© 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. 83
    Prev
    Next
    INDEX
    Explanations

    references to health-related issues, specifically diabetes and health assessments

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

    terms related to health and illness management

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

    neuro-metabolic diseases

    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
    ngrx
    -0.61
     cherchés
    -0.61
     efectivamente
    -0.51
     بيها
    -0.51
    endwhile
    -0.50
    GTCX
    -0.49
    :+:
    -0.49
     –,
    -0.48
     gegeven
    -0.47
     kautta
    -0.47
    POSITIVE LOGITS
     
    0.67
     Blood
    0.65
     Symptoms
    0.64
    KeySpec
    0.62
     Normal
    0.62
     What
    0.59
     blood
    0.57
    ագրություններ
    0.56
    #
    0.56
     brooms
    0.56
    Activations Density 0.011%

    No Known Activations