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. 53896
    Prev
    Next
    INDEX
    Explanations

    data structures and types related to programming languages

    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
    MigrationBuilder
    -0.68
    TagNumber
    -0.66
     /\.
    -0.64
    LookAnd
    -0.60
    createCell
    -0.60
    WaitGroup
    -0.60
     surla
    -0.59
    ://$
    -0.58
    WireFormatLite
    -0.57
    SBATCH
    -0.57
    POSITIVE LOGITS
    propTypes
    0.46
     Avez
    0.31
    原始内容存档于
    0.30
     PropTypes
    0.30
     Artículos
    0.29
    isRequired
    0.28
     Herramientas
    0.28
    oinette
    0.28
    homonymie
    0.28
     object
    0.27
    Activations Density 0.000%

    No Known Activations