© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1818
    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
    으로
    5.05
    े
    4.19
    y
    4.14
    𝑔
    4.09
    𝑟
    3.95
    𝑦
    3.77
    ो
    3.47
    residuals
    3.40
    𝒾
    3.31
    𝓁
    3.30
    POSITIVE LOGITS
    ties
    4.16
    s
    3.88
    ld
    3.81
     său
    3.54
    ॉजी
    3.37
    lds
    3.35
    ts
    3.25
     nostru
    3.21
    ্পনিক
    3.20
    тся
    3.16
    Activations Density 1.680%

    No Known Activations