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. 102959
    Prev
    Next
    INDEX
    Explanations

    quantifiable measurements and numerical data related to specific figures and concentrations

    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
     مشين
    -0.54
     виправивши
    -0.50
    FieldBuilder
    -0.46
    paux
    -0.45
    estris
    -0.45
     whereof
    -0.45
    principalTable
    -0.44
    parsedMessage
    -0.44
    mybatisplus
    -0.44
    mergeFrom
    -0.44
    POSITIVE LOGITS
    MENAFN
    0.50
    __':
    
    0.38
     ayudado
    0.33
    tagHelperRunner
    0.33
     criaturas
    0.32
    mientras
    0.32
     sementara
    0.32
    ⅘
    0.32
     empê
    0.31
     while
    0.31
    Activations Density 0.213%

    No Known Activations