© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1531
    Prev
    Next
    INDEX
    Explanations

    HTML elements and structure

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

    HTML comment tags and basic HTML structure elements

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

    sampled data

    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
    ycznej
    -0.58
     Headline
    -0.50
    valt
    -0.50
    bitField
    -0.48
    tieth
    -0.47
     Taxonomy
    -0.47
    unción
    -0.47
     描
    -0.46
    Билгалдахарш
    -0.46
    řad
    -0.46
    POSITIVE LOGITS
    contentLoaded
    0.76
    footer
    0.72
     footer
    0.71
     disambiguazione
    0.71
    GraphicsUnit
    0.66
     Audiodateien
    0.59
     Footer
    0.58
     Normdatei
    0.57
    
    0.57
     AssemblyCulture
    0.56
    Activations Density 0.019%

    No Known Activations