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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12238
    Prev
    Next
    INDEX
    Explanations

    autobiographical text, specifically stories about personal experiences, childhood, and aspirations.

    oai_token-act-pair · gemini-2.0-flash

    growing

    np_max-act-logits · gemini-2.0-flash

    personal pronouns like "I", "me", "my", and personal storytelling language.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @erichuang4312
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_23/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.78
    رشف
    -0.67
    __(/*!
    -0.48
     propOrder
    -0.48
     Original
    -0.45
    wts
    -0.44
     initComponents
    -0.44
    󠁢
    -0.43
     uska
    -0.43
     للمعارف
    -0.42
    POSITIVE LOGITS
     growing
    3.22
    growing
    2.91
     Growing
    2.83
    Growing
    2.75
     grow
    2.52
     GROW
    2.44
     grows
    2.38
     grew
    2.22
    grow
    2.13
     Grow
    2.09
    Activations Density 3.934%

    No Known Activations