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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6052
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations commonly used in equations or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ווי
    -0.50
    WriteLiteral
    -0.50
    θή
    -0.47
    Enlaces
    -0.45
    Distribu
    -0.45
    ftes
    -0.44
     Osten
    -0.44
     '>=
    -0.44
    uder
    -0.43
    acirc
    -0.43
    POSITIVE LOGITS
     Roskov
    0.99
    UrlResolution
    0.80
    enumi
    0.77
    prüche
    0.76
    MLLoader
    0.75
    providedIn
    0.71
    Tikang
    0.71
     متعلقه
    0.68
    enterOuterAlt
    0.67
    SuccessListener
    0.67
    Activations Density 1.020%

    No Known Activations