© 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 EvalsExportsAPI 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. 1779
    Prev
    Next
    INDEX
    Explanations

    components and classes related to web design and layout

    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
     maga
    -0.36
    bitField
    -0.35
     toch
    -0.35
     glyphicon
    -0.34
    glyphicon
    -0.34
    Im
    -0.33
     Im
    -0.33
    BitmapFactory
    -0.32
    mousemove
    -0.32
    BarStyle
    -0.31
    POSITIVE LOGITS
    verwijspagina
    0.73
    ロウィン
    0.68
    Tikang
    0.67
     فريبيس
    0.64
    GEBURTSDATUM
    0.64
     kasarigan
    0.62
     محفوظة
    0.60
    endphp
    0.60
     CURIAM
    0.58
    ineſs
    0.58
    Activations Density 0.677%

    No Known Activations