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-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13506
    Prev
    Next
    INDEX
    Explanations

    mentions of time periods, usually months or years, and occasionally words that sound alike

    oai_token-act-pair · gemini-2.0-flash

    Time periods, especially "month"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دة
    -0.43
    fpm
    -0.43
    asional
    -0.43
    )])
    -0.41
     Grüsse
    -0.41
     staten
    -0.40
    []}
    -0.40
    ート
    -0.40
     disproportion
    -0.40
    ItemBackground
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    0.96
     GoogleFonts
    0.79
    
    0.78
    fjspx
    0.76
     שוליים
    0.76
     nahilalakip
    0.74
    الدراسه
    0.73
     تضيفلها
    0.71
    تقاوى
    0.65
     Tequila
    0.65
    Activations Density 8.425%

    No Known Activations