© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7378
    Prev
    Next
    INDEX
    Explanations

    patterns in function definitions and public method declarations in programming code

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

    Code-related keywords

    np_acts-logits-general · gemini-2.0-flash

    programming keywords and code constructs

    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
    oredCriteria
    -0.62
    OCCURRED
    -0.58
     يتيمه
    -0.56
     SEDS
    -0.56
    aarrggbb
    -0.56
    QtWidgets
    -0.54
    await
    -0.54
    InitVars
    -0.54
    PagerAdapter
    -0.49
    SPATH
    -0.49
    POSITIVE LOGITS
     function
    1.33
    function
    1.32
     Function
    0.98
     función
    0.96
     funzione
    0.92
    函数
    0.90
    def
    0.88
     functie
    0.88
     함수
    0.88
     Funktion
    0.87
    Activations Density 0.104%

    No Known Activations