Refusal Register is Causally Steerable: Decomposing the Refusal Direction into Category-Aligned Components in Gemma-2-9B-IT

Prior work shows that refusal in instruction-tuned language models can be ablated by intervening on a single residual-stream direction (Arditi et al., 2024), and more recent work finds multiple refusal-mediating directions and concept cones (Wollschläger et al., 2025). We ask a different question: do refusal-related directions carry information about the register of refusal language - how the model refuses - and not only whether it refuses? In Gemma-2-9B-IT we identify two SVM-derived linear directions (B1 for harmful-content vs. neutral, B2 for self-reference vs. neutral) at layer 20 with cos(B1, B2) = 0.252 (about 75 degrees, substantially non-parallel). Adding the harmful-vs-neutral difference-of-means direction (cosine 0.68 with B1) to the residual stream of self-reference prompts at alpha = 2.0 shifts content-safety vocabulary from 2.55 to 10.37 hits per 100 tokens, while a magnitude-matched random direction produces 1.13-2.16; the model continues to refuse but switches register from meta-style ("as a language model...") to content-style ("this would be harmful"). The same register-injection effect reproduces qualitatively in Gemma-2-2B-IT at layer 12 (content vocabulary 1.72 -> 6.37 at alpha = 1.0, vs. random control 1.35), with a narrower coherent-injection window than in 9B. The two directions are not symmetric: the B2 -> harmful intervention produces a much smaller register effect, and across ablation, sufficiency, and injection B1's causal effects are consistently larger than B2's. We frame this asymmetry as part of the finding: B1 appears to encode both category detection and refusal-vocabulary information, while B2 encodes primarily category detection. We frame the contribution as identifying category-aligned components related to the Arditi-style difference-of-means direction that play distinct functional roles in refusal register.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.20405
Primary Topic
Explainable Artificial Intelligence (XAI)
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Refusal Register is Causally Steerable: Decomposing the Refusal Direction into Category-Aligned Components in Gemma-2-9B-IT

Janhavi Khindkar, Nataliia Povarova
1 links
arXiv (Cornell University)
Explainable Artificial Intelligence (XAI)
preprint

Refusal Register is Causally Steerable: Decomposing the Refusal Direction into Category-Aligned Components in Gemma-2-9B-IT

Janhavi Khindkar, Nataliia Povarova
preprint en

Abstract

Prior work shows that refusal in instruction-tuned language models can be ablated by intervening on a single residual-stream direction (Arditi et al., 2024), and more recent work finds multiple refusal-mediating directions and concept cones (Wollschläger et al., 2025). We ask a different question: do refusal-related directions carry information about the register of refusal language - how the model refuses - and not only whether it refuses? In Gemma-2-9B-IT we identify two SVM-derived linear directions (B1 for harmful-content vs. neutral, B2 for self-reference vs. neutral) at layer 20 with cos(B1, B2) = 0.252 (about 75 degrees, substantially non-parallel). Adding the harmful-vs-neutral difference-of-means direction (cosine 0.68 with B1) to the residual stream of self-reference prompts at alpha = 2.0 shifts content-safety vocabulary from 2.55 to 10.37 hits per 100 tokens, while a magnitude-matched random direction produces 1.13-2.16; the model continues to refuse but switches register from meta-style ("as a language model...") to content-style ("this would be harmful"). The same register-injection effect reproduces qualitatively in Gemma-2-2B-IT at layer 12 (content vocabulary 1.72 -> 6.37 at alpha = 1.0, vs. random control 1.35), with a narrower coherent-injection window than in 9B. The two directions are not symmetric: the B2 -> harmful intervention produces a much smaller register effect, and across ablation, sufficiency, and injection B1's causal effects are consistently larger than B2's. We frame this asymmetry as part of the finding: B1 appears to encode both category detection and refusal-vocabulary information, while B2 encodes primarily category detection. We frame the contribution as identifying category-aligned components related to the Arditi-style difference-of-means direction that play distinct functional roles in refusal register.

arXiv (Cornell University)
Explainable Artificial Intelligence (XAI)
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon