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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 117368
    Prev
    Next
    INDEX
    Explanations

    issues related to customer feedback and service performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Question markers in user queries or FAQ sections, where personal pronouns like "I" or "you" are often followed by modal verbs like "do," "can," or auxiliary verbs, ending with a question mark, sometimes with exclamation points for emphasis.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.49
    IsMutable
    -0.47
     cejas
    -0.39
     elástica
    -0.39
     recevrez
    -0.37
     tunggal
    -0.36
    ibatis
    -0.36
    awtextra
    -0.36
     pihaknya
    -0.36
     prisión
    -0.35
    POSITIVE LOGITS
     betweenstory
    0.59
    Portály
    0.52
     nahilalakip
    0.48
     متعلقه
    0.47
    makeText
    0.47
     uska
    0.45
    specialchars
    0.45
    RTLR
    0.45
     فريبيس
    0.45
     незавершена
    0.44
    Activations Density 0.116%

    No Known Activations