© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42427
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific formatting often found in academic or scientific writing

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

    CONFIG.mk CFLAGS.EXTRA

    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
     invokingState
    -0.56
    sizeCache
    -0.52
     referrerpolicy
    -0.50
    ftagPool
    -0.49
    astify
    -0.48
     BoxDecoration
    -0.48
    ->___
    -0.48
    Tembelea
    -0.47
    jasper
    -0.47
    脚注の使い方
    -0.47
    POSITIVE LOGITS
    endmodule
    0.47
     fallu
    0.41
    uxxxx
    0.40
    chappement
    0.40
    HomeAsUpEnabled
    0.39
     įsi
    0.34
    textsc
    0.34
    SuspendLayout
    0.34
    parsedMessage
    0.33
    EndGlobalSection
    0.32
    Activations Density 0.114%

    No Known Activations