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

    Neuronpedia

    APICircuit 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105104
    Prev
    Next
    INDEX
    Explanations

    references to component properties and structure in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     <>",
    -0.44
    bcryptjs
    -0.43
    tvguidetime
    -0.40
     protoimpl
    -0.38
    atimes
    -0.38
    TextBoxColumn
    -0.37
    点此举报
    -0.36
     AssemblyVersion
    -0.36
     tied
    -0.36
    delwed
    -0.35
    POSITIVE LOGITS
    nextProps
    0.90
     StatelessWidget
    0.74
    propTypes
    0.67
     propTypes
    0.65
     StatefulWidget
    0.63
    PreferredItem
    0.62
    defaultProps
    0.60
     InputDecoration
    0.58
    Props
    0.58
     PropTypes
    0.58
    Activations Density 0.003%

    No Known Activations