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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10682
    Prev
    Next
    INDEX
    Explanations

    coding and programming constructs, particularly assignment and increment operations

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

    Assignment operators (such as =, +=)

    np_acts-logits-general · gemini-2.0-flash

    assignment statements

    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
     otomatig
    -0.93
     المعيارى
    -0.80
     Мексичка
    -0.70
    neſs
    -0.60
     TextAppearance
    -0.58
     للاسماء
    -0.58
     שוליים
    -0.58
    InitStruct
    -0.55
     waarvan
    -0.55
     MainAxisSize
    -0.54
    POSITIVE LOGITS
    Hozzáférés
    0.64
    printStackTrace
    0.61
    Tetapi
    0.61
    CompleteListener
    0.60
    ⓧ
    0.59
    loài
    0.57
    Hauptartikel
    0.57
    poque
    0.56
     елның
    0.55
    jsoup
    0.55
    Activations Density 0.108%

    No Known Activations