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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 358
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    0.44
    ,
    0.40
    :
    0.40
    H
    0.39
    AS
    0.38
    ↵
    0.37
    ↵↵
    0.37
     (
    0.36
     *
    0.36
    com
    0.36
    POSITIVE LOGITS
     GoName
    0.77
    igating
    0.74
    izando
    0.73
    izing
    0.71
    utives
    0.70
    isation
    0.70
    itating
    0.70
    isiert
    0.70
    ativo
    0.69
    uating
    0.69
    Activations Density 0.805%

    No Known Activations