© 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
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 7517
    Prev
    Next
    INDEX
    Explanations

    files or components related to programming and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.85
    Хьажоргаш
    -0.71
    出版年
    -0.68
    IntoConstraints
    -0.66
    oredCriteria
    -0.65
    protoimpl
    -0.65
    脚注の使い方
    -0.64
    ніципалі
    -0.64
    CppMethod
    -0.64
    WriteBarrier
    -0.64
    POSITIVE LOGITS
    txt
    0.56
    dat
    0.45
     Herausforderung
    0.44
    log
    0.42
     propietarios
    0.42
    sh
    0.41
     vantagem
    0.40
     dítě
    0.40
    properties
    0.39
    PROPERTIES
    0.39
    Activations Density 0.467%

    No Known Activations