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. 243
    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
    input
    0.42
    ↵
    0.40
    self
    0.40
    int
    0.40
    left
    0.40
    body
    0.39
    problem
    0.39
    text
    0.38
    padding
    0.37
    POSITIVE LOGITS
     Announces
    1.04
     Presents
    0.90
     Offers
    0.84
     Holdings
    0.82
     Corporation
    0.82
    ®,
    0.82
     Launches
    0.81
    ®.
    0.80
     Partnership
    0.79
     รุ่น
    0.75
    Activations Density 7.327%

    No Known Activations