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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 614
    Prev
    Next
    INDEX
    Explanations

    references to manufacturers and publishers

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

    terms related to suppliers and manufacturers

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

    manufacturers, suppliers, and publishers

    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
    parsedMessage
    -0.95
     resourceCulture
    -0.94
    AutoScaleMode
    -0.81
     Мексичка
    -0.80
     виправивши
    -0.79
    extAlignment
    -0.75
    ValueGeneration
    -0.73
    protoimpl
    -0.72
    ChildScrollView
    -0.72
     Roskov
    -0.72
    POSITIVE LOGITS
     firm
    0.59
     supplying
    0.57
    JoinColumn
    0.57
     partners
    0.57
     firms
    0.56
     tarjo
    0.56
    ství
    0.52
     suppliers
    0.50
    '
    0.49
    /
    0.47
    Activations Density 0.076%

    No Known Activations