© 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. 736
    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
    こと
    3.09
    أ
    2.95
    此之外
    2.85
    ことです
    2.84
     bunch
    2.74
    ので
    2.74
    ー
    2.71
    gador
    2.63
    i
    2.62
     быть
    2.57
    POSITIVE LOGITS
     exped
    2.79
     objectMapper
    2.63
     olefins
    2.56
    лити
    2.45
    saturated
    2.36
    isto
    2.35
    rowad
    2.32
    filepath
    2.32
    ize
    2.24
    いる
    2.20
    Activations Density 1.355%

    No Known Activations