© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 4159
    Prev
    Next
    INDEX
    Explanations

    patterns of code formatting and syntactical structures in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.63
    UnsafeEnabled
    -0.61
     gently
    -0.56
    pgterms
    -0.55
    WriteTagHelper
    -0.54
    ThroughAttribute
    -0.54
    دانشنامهٔ
    -0.53
    AccessorTable
    -0.51
     noDo
    -0.51
    MarshalTo
    -0.49
    POSITIVE LOGITS
    Tikang
    0.52
    ագրություններ
    0.37
     Wikimedijinoj
    0.36
     médicaux
    0.36
     intellectuelle
    0.33
     acrylique
    0.32
    ście
    0.32
     thermique
    0.31
     bağlı
    0.31
    aturing
    0.31
    Activations Density 0.638%

    No Known Activations