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. 3739
    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
    ע
    1.49
     العامة
    1.48
    områ
    1.43
    ו
    1.42
    शास्त्र
    1.36
    ພ
    1.35
    reetype
    1.32
    отно
    1.31
    מוד
    1.31
    ரசுக்
    1.27
    POSITIVE LOGITS
     끝
    0.97
     shrunk
    0.96
     sizes
    0.96
     Asking
    0.94
     sides
    0.93
     끼
    0.93
     whe
    0.93
    ERA
    0.92
     whats
    0.91
     swinging
    0.91
    Activations Density 0.002%

    No Known Activations