© 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. 223
    Prev
    Next
    INDEX
    Explanations

    references to individuals, populations, or groups in a medical context

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

    references to people and populations in relation to health conditions

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

    people with conditions

    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
    Personensuche
    -1.14
    AddTagHelper
    -1.05
    twimg
    -0.85
     الاطلاع
    -0.85
    MemoryWarning
    -0.83
    GEBURTSDATUM
    -0.79
    ngdoc
    -0.79
     مرئيه
    -0.79
     فريبيس
    -0.78
    
    -0.78
    POSITIVE LOGITS
     with
    0.77
     not
    0.72
     in
    0.68
     just
    0.62
     still
    0.62
     currently
    0.58
     on
    0.58
     having
    0.58
     of
    0.58
     already
    0.55
    Activations Density 0.196%

    No Known Activations