© 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. 2-GEMMASCOPE-RES-16K
    11. 15004
    Prev
    Next
    INDEX
    Explanations

    structures related to programming code or syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.77
     nahilalakip
    -0.77
     defaultstate
    -0.74
    esModule
    -0.73
     faſt
    -0.73
    MigrationBuilder
    -0.70
     ſind
    -0.69
    iſen
    -0.68
    niſſe
    -0.68
    principalTable
    -0.65
    POSITIVE LOGITS
    ↵↵
    0.50
    ,
    0.45
     
    0.43
     (
    0.39
     the
    0.36
    (
    0.35
    ắt
    0.35
     and
    0.34
     konusunda
    0.34
     Harris
    0.34
    Activations Density 0.272%

    No Known Activations