Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Blog/Podcast
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog/Podcast
GitHub
Slack
Twitter
Contact
Vector Label
refusal (Arditi et al. 2024)
Model
gemma-2-2b-it
Layer #
15
Steering Hook
blocks.15.hook_resid_pre
Steering Strength
0.25
Uploader
bot-neuronpedia
Created At
11/20/2024 9:49:19 AM
Raw Vector
Actions
Steer
Explanations
No Explanations Found
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b-it/15-neuronpedia-resid-pre/0?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b-it/15-neuronpedia-resid-pre/0?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Test
Steer
No Known Activations
