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
10896
Prev
Next
MODEL
20-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
mathematical symbols and notations
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
Mathematical symbols followed by a plus or minus sign
np_acts-logits-general · gemini-2.0-flash
No Scores
positive mathematical operators
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
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-2-2b/20-gemmascope-res-16k/10896?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/20-gemmascope-res-16k/10896?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
)");
-0.72
)";
-0.71
]]);
-0.69
GHIJKLM
-0.68
]]
-0.68
MENAFN
-0.67
]();
-0.66
parseFrom
-0.66
)"),
-0.65
IVEREF
-0.64
POSITIVE LOGITS
+
1.36
+
1.12
$+
0.99
plus
0.80
+
0.75
+
0.74
plus
0.73
Plus
0.73
$+
0.71
Plus
0.70
Act
ivations
Density 1.140%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations