Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
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
10347
Prev
Next
MODEL
25-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
references to women in the context of implications for fertility and reproduction
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
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/25-gemmascope-res-16k/10347?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/25-gemmascope-res-16k/10347?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
1
-1.84
１
-1.03
১
-0.95
১
-0.84
१
-0.83
١
-0.73
१
-0.72
١
-0.71
¹
-0.69
₁
-0.68
POSITIVE LOGITS
يتيمه
0.64
۴
0.63
InjectAttribute
0.62
۶
0.62
fün
0.60
۷
0.60
SEVEN
0.59
۵
0.58
۸
0.57
fifth
0.56
Act
ivations
Density 1.359%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
