Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6147
    Prev
    Next
    INDEX
    Explanations

    references to styles and assembly attributes in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.60
    ellido
    -0.58
    ufficio
    -0.58
     Exact
    -0.56
    pygame
    -0.56
     quæ
    -0.56
     whoſe
    -0.55
    كويكب
    -0.55
    ixante
    -0.54
     noses
    -0.54
    POSITIVE LOGITS
    AspNetCore
    1.12
     nahilalakip
    0.84
    Tembelea
    0.75
    __(/*!
    0.71
    ThroughAttribute
    0.71
    addGroup
    0.70
    dispatch
    0.67
    Controllo
    0.65
    rawDesc
    0.64
    存于互联网档案馆
    0.60
    Activations Density 0.035%

    No Known Activations