© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 840
    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_9_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
    koliko
    0.86
    নাথ
    0.81
    be
    0.79
    gebracht
    0.79
    g
    0.77
    voor
    0.75
    岖
    0.74
     plunger
    0.73
     liar
    0.73
    muestra
    0.73
    POSITIVE LOGITS
    ️
    0.77
    ▫
    0.62
    //*
    0.62
    ت
    0.60
     bhp
    0.57
    ⅞
    0.57
    ια
    0.57
    ἱ
    0.55
    age
    0.55
    즌
    0.54
    Activations Density 3.748%

    No Known Activations