Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 131036
    Prev
    Next
    INDEX
    Explanations

    specifications and parameters related to signal processing and layout design in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.39
    周
    -0.38
    alt
    -0.37
     lainnya
    -0.35
    cc
    -0.35
    other
    -0.34
     Audiodateien
    -0.33
    丁
    -0.33
     apprécié
    -0.33
    About
    -0.33
    POSITIVE LOGITS
    IntoConstraints
    0.85
    tagHelperRunner
    0.82
    PostInfinity
    0.64
     AssemblyCulture
    0.63
    posedge
    0.62
    ftagPool
    0.57
    kháu
    0.56
    Carriera
    0.56
    tonode
    0.56
    Hentet
    0.56
    Activations Density 0.063%

    No Known Activations