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. 476
    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
     (
    0.99
     un
    0.92
     over
    0.85
     in
    0.81
    ,
    0.80
     a
    0.79
     back
    0.78
     at
    0.76
     with
    0.76
     baby
    0.75
    POSITIVE LOGITS
    BuildActionEntry
    1.12
     Paryayvachi
    1.08
     коюмдары
    1.06
    Usuario
    1.06
    
    1.04
     Mitgl
    1.03
    參数
    1.02
     букмекерлар
    1.01
    Ṕ
    0.99
    UserProg
    0.99
    Activations Density 5.894%

    No Known Activations