© 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-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 8598
    Prev
    Next
    INDEX
    Explanations

    references to gloves and witch-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InstanceState
    -0.59
    DropColumn
    -0.59
     iprot
    -0.55
     مرئيه
    -0.55
    endphp
    -0.55
    WriteLiteral
    -0.55
     ModelRenderer
    -0.54
    jspx
    -0.53
    endregion
    -0.52
    排
    -0.49
    POSITIVE LOGITS
    reciated
    0.69
     оригіналу
    0.68
     ***!
    0.68
     Witches
    0.67
    liothèque
    0.67
     Roskov
    0.66
    actylus
    0.66
    üyada
    0.65
     arbo
    0.65
     Ket
    0.64
    Activations Density 0.023%

    No Known Activations