© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16110
    Prev
    Next
    INDEX
    Explanations

    phrases indicating varying degrees of extent or limitation

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

    "To a [degree/extent]" phrasing

    np_acts-logits-general · gemini-2.0-flash

    qualified degree or extent

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    UrlResolution
    -0.75
     BoxDecoration
    -0.68
    исленность
    -0.68
     BrowserModule
    -0.64
     '\\;'
    -0.64
     OFDb
    -0.63
    出版年
    -0.62
     CreateTagHelper
    -0.61
    CodeDom
    -0.61
     ModelExpression
    -0.61
    POSITIVE LOGITS
     extent
    1.71
     degree
    1.56
    extent
    1.43
     Extent
    1.28
    degree
    1.25
     Degree
    1.21
     degrees
    1.15
     extend
    1.15
    Degree
    1.14
    Extent
    1.14
    Activations Density 0.165%

    No Known Activations