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. 341
    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
    T
    0.56
     the
    0.55
    W
    0.53
    com
    0.52
    A
    0.50
    C
    0.50
    P
    0.50
    ac
    0.49
    S
    0.49
    1
    0.48
    POSITIVE LOGITS
    <unused764>
    1.06
    );//
    1.04
    );
    1.03
    𐰇
    1.03
    ;//
    1.02
    
    1.00
    <unused2060>
    0.98
     auxqu
    0.98
    ৤
    0.98
     messageShow
    0.97
    Activations Density 2.705%

    No Known Activations