© 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. 509
    Prev
    Next
    INDEX
    Explanations

    references to governmental actions and approvals

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

    references to organizational governance and decision-making processes

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

    legislative voting and approval

    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
     auprès
    -0.63
    ngen
    -0.46
    CPtr
    -0.46
     tirada
    -0.43
    ariato
    -0.42
    numerusform
    -0.42
     offend
    -0.42
     משפ
    -0.42
     minist
    -0.42
     contacting
    -0.42
    POSITIVE LOGITS
     unanimously
    1.15
     voted
    0.94
     approving
    0.89
     approve
    0.88
     approval
    0.87
     unanimous
    0.85
     vote
    0.85
     approved
    0.80
     unanim
    0.80
     aprobó
    0.79
    Activations Density 0.132%

    No Known Activations