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. 15238
    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
    advant
    2.29
    VELOP
    2.26
    ende
    2.19
    ône
    2.19
    apia
    2.15
     Ranch
    2.07
    a
    2.06
    ME
    2.04
    RICT
    2.03
    өт
    2.02
    POSITIVE LOGITS
    ൮
    2.72
    𝘵
    2.46
    दारा
    2.39
    tts
    2.36
    tocol
    2.35
    Viral
    2.31
    tie
    2.29
    ties
    2.27
    デュー
    2.27
    帑
    2.26
    Activations Density 0.145%

    No Known Activations