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
18-GEMMASCOPE-RES-16K
8556
Prev
Next
MODEL
18-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
mathematical equations and notation
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
Mathematical or symbolic sequences/expressions
np_acts-logits-general · gemini-2.0-flash
No Scores
mathematical sequences with ellipsis
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 @ 18-gemmascope-res-16k
Configuration
google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
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.18.hook_resid_post
Hook Layer
18
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/18-gemmascope-res-16k/8556?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/18-gemmascope-res-16k/8556?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
）』
-0.94
.")
-0.88
!")
-0.86
'},
-0.86
)");
-0.86
)";
-0.84
")]
-0.81
`;
-0.81
}}$}
-0.80
=[]
-0.78
POSITIVE LOGITS
...
2.25
...
2.13
…
2.13
....
2.03
…
1.91
….
1.88
.....
1.87
……
1.86
....
1.82
......
1.81
Act
ivations
Density 1.690%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
