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. 128
    Prev
    Next
    INDEX
    Explanations

    elements related to message structures in programming, particularly with an emphasis on protocols and types

    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
    +:+
    -0.52
     سكانية
    -0.50
    춤
    -0.48
    ValueStyle
    -0.48
    igten
    -0.47
     MLM
    -0.47
     dikk
    -0.46
     YI
    -0.46
     Și
    -0.46
     pigeons
    -0.45
    POSITIVE LOGITS
    $_['
    0.70
     iprot
    0.68
     defaultstate
    0.67
    ThroughAttribute
    0.66
     JpaRepository
    0.63
    saraba
    0.61
    EDEFAULT
    0.61
     propOrder
    0.60
    PathParam
    0.60
    reportWebVitals
    0.59
    Activations Density 0.003%

    No Known Activations