© 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. 53
    Prev
    Next
    INDEX
    Explanations

    variations of the word "Dun" across the text

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

    the name "Dun" in various contexts

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

    starts with Dun

    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
    LookAnd
    -0.66
    彡
    -0.64
    batore
    -0.64
     glyphicon
    -0.63
    roller
    -0.63
     betweenstory
    -0.62
    ROLLER
    -0.61
    klä
    -0.60
     predecess
    -0.57
    subpackage
    -0.56
    POSITIVE LOGITS
     Dun
    0.88
    Dun
    0.86
     DUN
    0.73
     dun
    0.73
     Dunlap
    0.60
    WarningLevel
    0.55
    DUN
    0.55
    dun
    0.52
     Dunham
    0.51
    دن
    0.51
    Activations Density 0.013%

    No Known Activations