© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 471
    Prev
    Next
    INDEX
    Explanations

    actions related to preparation and cooking processes

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

    terms related to cooking techniques and food preparation

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

    excess or surplus

    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
     समीक्षक
    -0.78
    principalColumn
    -0.69
    ]")]
    -0.68
    ⓧ
    -0.63
     propOrder
    -0.63
    ValueStyle
    -0.61
     ویکی‌پدیا
    -0.59
    PositiveButton
    -0.58
    出版年
    -0.57
    ueuse
    -0.57
    POSITIVE LOGITS
     excess
    1.07
    excess
    0.88
     Excess
    0.87
     excesso
    0.84
    Excess
    0.83
     exceso
    0.78
     surplus
    0.72
     excès
    0.69
     any
    0.64
     лиш
    0.62
    Activations Density 0.077%

    No Known Activations