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. 345
    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
    ↵↵
    0.50
    :
    0.38
    ,
    0.35
    <start_of_image>
    0.34
    <0x0D>
    0.33
    ers
    0.31
    -
    0.30
    .
    0.30
    </h2>
    0.30
    ities
    0.28
    POSITIVE LOGITS
     Và
    0.73
     是否
    0.71
     当然
    0.69
     Nhưng
    0.67
     podendo
    0.65
     Какой
    0.65
     Bahkan
    0.65
     Также
    0.64
     所以
    0.64
     或者
    0.64
    Activations Density 8.764%

    No Known Activations