© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2954
    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
    <eos>
    1.05
     […]
    0.96
    tv
    0.95
    iously
    0.94
    itating
    0.92
    假日
    0.92
     incomes
    0.91
    c
    0.91
    gments
    0.91
    atively
    0.90
    POSITIVE LOGITS
     Role
    1.56
     Subset
    1.50
     Visualization
    1.49
     Workflow
    1.48
     Revisited
    1.48
     Connectivity
    1.47
     Reality
    1.46
     Setting
    1.45
     Challenge
    1.43
     Creativity
    1.41
    Activations Density 0.737%

    No Known Activations