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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 556
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to programming and document formatting

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

    references to character encoding standards, particularly UTF

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

    mathematical fractions or specific symbols

    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
     kasarigan
    -0.90
    aarrggbb
    -0.77
    исленность
    -0.74
    InitVars
    -0.72
    IntoConstraints
    -0.72
     دیکھیے
    -0.70
    AddHtmlAttribute
    -0.69
    webElement
    -0.68
    mybatisplus
    -0.67
    ArrowToggle
    -0.64
    POSITIVE LOGITS
    UTF
    0.75
     FontWeight
    0.69
    styleable
    0.65
    PageIndex
    0.65
    ientí
    0.59
    enumi
    0.57
     UTF
    0.55
    enumii
    0.55
     stead
    0.53
    KEYCODE
    0.52
    Activations Density 0.001%

    No Known Activations