Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1210
    Prev
    Next
    INDEX
    Explanations

    sequences of numeric values, particularly dates or numerical data

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

    instances of significant numerical data or citations

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

    years ending in 9

    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
    الإنجليزية
    -0.75
     AspNetCore
    -0.70
     '\\;'
    -0.66
    lably
    -0.57
    BeginContext
    -0.57
     للمعارف
    -0.54
    Източници
    -0.53
     /\.(
    -0.53
    تقاوى
    -0.52
    ngdoc
    -0.52
    POSITIVE LOGITS
    Portale
    0.60
    vábbi
    0.50
    WebVitals
    0.50
     sixties
    0.49
     Rhodesia
    0.49
    asibility
    0.49
     liné
    0.48
     privatisation
    0.48
     iconos
    0.48
     seventies
    0.47
    Activations Density 0.129%

    No Known Activations