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. 15125
    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
    ່ານ
    1.43
    ס
    1.36
     padding
    1.30
    assured
    1.29
    QueryResult
    1.26
    倒是
    1.25
     ثقاف
    1.24
     جناب
    1.23
     लक्षात
    1.20
    珅
    1.20
    POSITIVE LOGITS
    ときに
    1.47
    とき
    1.42
    ときは
    1.29
     McLaughlin
    1.26
    𝐥
    1.26
     momento
    1.25
     пъ
    1.25
     moment
    1.23
    𝐫
    1.20
     torsion
    1.17
    Activations Density 0.002%

    No Known Activations