© 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. 22-GEMMASCOPE-RES-16K
    11. 2091
    Prev
    Next
    INDEX
    Explanations

    open and close parentheses

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

    Code: for loops, if statements, or variable declarations

    np_acts-logits-general · gemini-2.0-flash

    programming code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -1.03
    脚注の使い方
    -0.92
    OGND
    -0.81
    MigrationBuilder
    -0.80
     estimés
    -0.80
    '}>
    -0.77
     مشين
    -0.77
    []
    -0.77
     Мексичка
    -0.73
     المعيارى
    -0.73
    POSITIVE LOGITS
    ;;
    0.77
    int
    0.75
    var
    0.65
    PerformLayout
    0.64
     ;
    0.64
     ;;
    0.62
    Iterator
    0.58
    size
    0.57
     size
    0.57
     int
    0.54
    Activations Density 0.017%

    No Known Activations