© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14648
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "sort" indicating categorization or classification

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

    Comes before "of" and after "sort"

    np_acts-logits-general · gemini-2.0-flash

    sort of

    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
    LLocation
    -0.64
    <h4>
    -0.61
    Extinguishing
    -0.60
    contentLoaded
    -0.57
    mampuan
    -0.56
    typeparam
    -0.55
    <h2>
    -0.54
    ちな
    -0.53
    ViewFeatures
    -0.53
     Zeeland
    -0.53
    POSITIVE LOGITS
     SORT
    0.90
     Sort
    0.78
     sort
    0.73
     sorts
    0.70
    RegressionTest
    0.69
    sor
    0.68
     Sorting
    0.63
     SOR
    0.63
    ंदीखरीदारी
    0.62
     Sor
    0.61
    Activations Density 0.038%

    No Known Activations