© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 545
    Prev
    Next
    INDEX
    Explanations

    references to court systems and related legal terminology

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

    references to dates and events

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

    locations in North Carolina

    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
    Personendaten
    -0.77
     nakalista
    -0.69
     متعلقه
    -0.65
     FetchType
    -0.60
    setupUi
    -0.59
    
    -0.58
    IContainer
    -0.57
    +#+
    -0.57
     endwhile
    -0.56
     ProtoMessage
    -0.54
    POSITIVE LOGITS
    setVerticalGroup
    0.66
     Yad
    0.50
    ую
    0.48
    []){
    0.45
    itorial
    0.44
    ✫
    0.44
     Thousand
    0.44
    antiation
    0.44
     निक
    0.43
     ชั้น
    0.43
    Activations Density 0.112%

    No Known Activations