© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 61082
    Prev
    Next
    INDEX
    Explanations

    curly braces and their nested structures in LaTeX formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX mathematical environments (cases, pmatrix, align)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -1.11
     MainAxisSize
    -1.09
    出版年
    -1.04
    ſammen
    -1.02
     témoig
    -1.02
    majánló
    -0.99
     OFDb
    -0.99
    
    -0.98
    RegressionTest
    -0.97
     increí
    -0.96
    POSITIVE LOGITS
    {
    0.63
    tabular
    0.53
    [
    0.50
    <
    0.48
    1
    0.46
     {
    0.46
    9
    0.45
     new
    0.44
    (
    0.43
     [
    0.43
    Activations Density 0.015%

    No Known Activations