© 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. 1214
    Prev
    Next
    INDEX
    Explanations

    the word "or" in contexts suggesting alternatives or choices

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

    "Or" followed by "may" or "not"

    np_acts-logits-general · gemini-2.0-flash

    may or may not

    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
    :"-"`
    -0.63
     jinak
    -0.59
     dagegen
    -0.54
    ordinaire
    -0.52
     الإنترنت
    -0.50
    brandt
    -0.48
    TEMPO
    -0.48
    URIComponent
    -0.48
    claire
    -0.47
    上
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.80
     GetEnumerator
    0.67
    TagMode
    0.56
    ResponseWriter
    0.56
    qz
    0.56
     BoxFit
    0.55
    PageFactory
    0.55
     समीक्षाओं
    0.55
     חיצוניים
    0.54
     orm
    0.53
    Activations Density 0.113%

    No Known Activations