© 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. 2010
    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
    फेसर
    2.10
    spapers
    1.95
    tesy
    1.91
    ো
    1.90
    adaşlar
    1.76
    r
    1.71
    ेट
    1.67
    Рис
    1.66
    rary
    1.65
     Sehr
    1.63
    POSITIVE LOGITS
    CH
    1.65
    idad
    1.60
    排放
    1.52
     axon
    1.49
    cope
    1.48
    ष्‍ट्र
    1.48
    菪
    1.47
    未満
    1.46
     связан
    1.45
    Me
    1.45
    Activations Density 0.378%

    No Known Activations