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
20-GEMMASCOPE-RES-16K
14515
Prev
Next
MODEL
20-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
phrases related to legal concerns and criminal activities
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
Text after names or titles
np_acts-logits-general · gemini-2.0-flash
No Scores
rides on webpages
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-2B @ 20-gemmascope-res-16k
Configuration
google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
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.20.hook_resid_post
Hook Layer
20
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/20-gemmascope-res-16k/14515?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/20-gemmascope-res-16k/14515?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
%");
-0.86
='';
-0.74
'));
-0.72
`;
-0.72
)");
-0.70
?");
-0.69
%";
-0.69
(");
-0.68
✨:
-0.68
"):
-0.67
POSITIVE LOGITS
Read
1.33
Read
1.32
read
1.24
read
1.23
http
1.17
READ
1.11
Continue
1.08
https
1.03
READ
0.98
http
0.98
Act
ivations
Density 0.146%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
