Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 1351
    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
     lim
    0.89
    ᱷ
    0.85
    搭建
    0.78
     limiting
    0.76
    养
    0.73
     வளர்
    0.72
     выращи
    0.72
    畸
    0.72
    構築
    0.70
    庭
    0.70
    POSITIVE LOGITS
     button
    2.81
     buttons
    2.74
    按钮
    2.60
     Button
    2.55
    button
    2.54
    Button
    2.51
     botão
    2.44
     botón
    2.41
     Buttons
    2.38
     tombol
    2.31
    Activations Density 1.554%

    No Known Activations