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. 367
    Prev
    Next
    INDEX
    Explanations

    programming terms related to transitions and asynchronous processes

    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
    ViewInit
    -0.78
    \{\\
    -0.77
    𓃵
    -0.77
    ^(@)
    -0.76
    órc
    -0.75
    elerik
    -0.74
    NUMX
    -0.73
     esempi
    -0.73
    --]
    -0.73
    cheiben
    -0.72
    POSITIVE LOGITS
     tkan
    0.61
    Abitanti
    0.56
    ↵↵
    0.54
     onAnimation
    0.54
     Twitch
    0.54
     Kirsch
    0.54
    Twitch
    0.53
    createStatement
    0.52
     stit
    0.52
    Mord
    0.52
    Activations Density 0.002%

    No Known Activations