© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28213
    Prev
    Next
    INDEX
    Explanations

    the beginning of sentences or sections marked by specific symbols

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

    units of measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.93
    thâu
    -0.92
    !*\
    -0.85
     nahilalakip
    -0.83
    URLException
    -0.81
    ConstraintMaker
    -0.77
    archiviato
    -0.75
     <>",
    -0.74
    ">//
    -0.73
     estimés
    -0.70
    POSITIVE LOGITS
    
    0.72
     grams
    0.63
    reactivex
    0.61
     sachet
    0.60
    dac
    0.58
     biber
    0.58
     ounce
    0.57
     ounces
    0.56
     teaspoons
    0.56
    зец
    0.55
    Activations Density 0.074%

    No Known Activations