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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6811
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data related to households and family structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.42
    InputBorder
    -0.40
    ADELPHIA
    -0.34
     surla
    -0.34
    endphp
    -0.32
     ✭✭
    -0.30
    หน้านี้
    -0.30
    adaptiveStyles
    -0.30
    äsident
    -0.30
     RoutedEventArgs
    -0.30
    POSITIVE LOGITS
     partnerships
    0.73
     team
    0.71
     teaming
    0.69
     teams
    0.67
     teamed
    0.65
     partnership
    0.65
     pairs
    0.65
     pairings
    0.64
     TEAM
    0.64
     pairing
    0.61
    Activations Density 0.578%

    No Known Activations