© 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. 1509
    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
    𝒍
    3.97
    𝒓
    3.76
    𝒔
    3.64
    ক
    3.49
    𝖘
    3.45
    𝒃
    3.44
    𝒅
    3.39
    𝒌
    3.33
    𝒙
    3.33
    𝖑
    3.13
    POSITIVE LOGITS
    m
    4.04
    an
    3.84
    at
    3.74
    ان
    3.61
    lardan
    3.52
    anel
    3.27
    larda
    3.25
    вість
    3.24
    ر
    3.18
    า
    3.13
    Activations Density 1.516%

    No Known Activations