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-2-2B
    4. Residual Post
    5. 12-GEMMASCOPE-RES-1M
    6. 92
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and refunds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    databind
    -0.68
     لينك
    -0.62
    rrggbb
    -0.59
    IntoConstraints
    -0.58
     AspNetCore
    -0.54
     ſtate
    -0.54
    djangoproject
    -0.54
    ^(@)
    -0.54
    anskje
    -0.51
    manns
    -0.51
    POSITIVE LOGITS
    StylePriority
    0.61
    MigrationBuilder
    0.59
    dib
    0.57
    rasında
    0.54
     Regularly
    0.54
    程
    0.54
     espécie
    0.52
    ător
    0.51
    exitRule
    0.51
     persino
    0.51
    Activations Density 0.001%

    No Known Activations