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
16-GEMMASCOPE-RES-16K
12928
Prev
Next
MODEL
16-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
references to chemical elements or compounds
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
Capitalized abbreviations or names
np_acts-logits-general · gemini-2.0-flash
No Scores
Ba, Ma, Sa, Ha, pa prefixes
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 @ 16-gemmascope-res-16k
Configuration
google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
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.16.hook_resid_post
Hook Layer
16
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/16-gemmascope-res-16k/12928?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/16-gemmascope-res-16k/12928?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
itſelf
-0.94
་་
-0.87
Theſe
-0.87
―――――
-0.84
faſt
-0.84
ſind
-0.79
iſt
-0.78
remer
-0.78
myſelf
-0.77
verſ
-0.76
POSITIVE LOGITS
Ra
0.93
Su
0.91
Ma
0.87
Ba
0.86
Su
0.86
Ge
0.86
Ra
0.84
Ne
0.83
Pe
0.83
Ro
0.83
Act
ivations
Density 0.388%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
