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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 521
    Prev
    Next
    INDEX
    Explanations

    JavaScript function calls and their associated parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    JavaScript function calls and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    web code and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    AccessorTable
    -0.76
    ✨:
    -0.71
    Спасылкі
    -0.64
    Дереккөздер
    -0.62
     للمعارف
    -0.61
    sizeCache
    -0.60
     Мексичка
    -0.58
     بيها
    -0.57
     Efq
    -0.57
    最快更新
    -0.57
    POSITIVE LOGITS
    STRUCTIONS
    0.59
     الدولى
    0.57
    Royce
    0.55
    {}
    0.53
     postre
    0.53
     Pauly
    0.50
    ReusableCell
    0.49
    kać
    0.49
    ustand
    0.48
    ardust
    0.47
    Activations Density 0.010%

    No Known Activations