Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Google DeepMind · Exploring Gemma 2 with Gemma Scope
Gemma-2-2B
Residual Stream - 16k
25-GEMMASCOPE-RES-16K
8768
Prev
Next
MODEL
25-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
fear-related language and emotional responses tied to external events
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-2B @ 25-gemmascope-res-16k
Configuration
google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
How To Load
Prompts (Dashboard)
36,864 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.25.hook_resid_post
Hook Layer
25
Architecture
jumprelu
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Activation Function
relu
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-2-2b/25-gemmascope-res-16k/8768?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/25-gemmascope-res-16k/8768?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
Ind
-1.53
IND
-1.50
Ind
-1.37
IND
-1.31
ind
-1.14
ind
-1.14
Indigo
-1.12
Indigo
-1.05
Indra
-1.05
Indy
-1.03
POSITIVE LOGITS
Joo
0.87
Julia
0.84
Judas
0.83
Juli
0.83
Sandy
0.81
Judith
0.80
JUL
0.79
Douglas
0.78
juli
0.76
Julia
0.75
Act
ivations
Density 1.587%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
