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. 558
    Prev
    Next
    INDEX
    Explanations

    terms related to software licensing and distribution

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

    legal terminology related to software distribution and licensing

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

    creative commons attribution

    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
     Roskov
    -0.90
    makeConstraints
    -0.85
     архивлан
    -0.81
    queryInterface
    -0.79
     Италијани
    -0.78
    IndentedString
    -0.76
     समीक्षक
    -0.75
     ModelExpression
    -0.74
    protoimpl
    -0.74
     MainAxisSize
    -0.73
    POSITIVE LOGITS
    OURCE
    0.49
     gesto
    0.36
     moment
    0.36
    хло
    0.35
    ガニック
    0.35
    tages
    0.35
     formy
    0.34
    假
    0.34
     pressure
    0.34
     있습니다
    0.34
    Activations Density 0.013%

    No Known Activations