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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103974
    Prev
    Next
    INDEX
    Explanations

    references to sources or origins in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    alakip
    -0.54
    tispiece
    -0.51
    retudo
    -0.51
     atracción
    -0.47
     interpretación
    -0.47
     assistência
    -0.46
    šanās
    -0.45
     înc
    -0.44
     explicación
    -0.43
     exámenes
    -0.42
    POSITIVE LOGITS
    minecraftforge
    0.56
    providedIn
    0.55
    WriteLiteral
    0.52
    原始内容存档
    0.48
    areas
    0.48
     higher
    0.46
     lenker
    0.46
    };*/
    0.46
     areas
    0.43
    bVar
    0.43
    Activations Density 0.073%

    No Known Activations