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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 15139
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    について
    1.32
    Me
    1.30
    สำหรับ
    1.30
    TM
    1.30
    Le
    1.27
    Name
    1.25
    ล
    1.25
    ศึกษา
    1.23
    স
    1.22
    С
    1.21
    POSITIVE LOGITS
    wpilibj
    1.64
     brutal
    1.61
     fundamentally
    1.57
     overtly
    1.56
    <unused1252>
    1.50
     gradual
    1.50
     instinctively
    1.50
     rigid
    1.50
     然而
    1.49
     penta
    1.48
    Activations Density 0.008%

    No Known Activations