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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 236
    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
    F
    0.69
    ה
    0.68
    But
    0.64
    M
    0.63
    However
    0.63
    W
    0.63
    ه
    0.62
    A
    0.62
    H
    0.60
    м
    0.60
    POSITIVE LOGITS
     whatnot
    1.09
     therefore
    1.08
     thus
    1.08
     consequently
    1.03
     hence
    1.01
     possibly
    1.01
     ultimately
    1.00
     subsequently
    1.00
     somit
    0.97
     arguably
    0.96
    Activations Density 1.812%

    No Known Activations