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
18-GEMMASCOPE-RES-16K
10282
Prev
Next
MODEL
18-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
elements and attributes related to user interface components, specifically in a web application context
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
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
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/18-gemmascope-res-16k/10282?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/18-gemmascope-res-16k/10282?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
)");
-1.25
)";
-1.16
`;
-1.03
%")
-1.02
Paglinawan
-0.98
.";
-0.98
}")
-0.98
"):
-0.96
"]);
-0.93
>";
-0.91
POSITIVE LOGITS
</
0.86
&
0.70
!
0.68
</td>
0.67
|
0.66
</h2>
0.62
\
0.61
:)
0.61
<
0.60
",
0.59
Act
ivations
Density 0.238%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations