Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 53073
    Prev
    Next
    INDEX
    Explanations

    terms related to stock market orders and liquidity dynamics

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

    trading and price changes

    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
    כי
    -0.43
     visitas
    -0.42
    cso
    -0.40
     poly
    -0.40
    ูป
    -0.40
     branca
    -0.39
     peccato
    -0.39
    Visitor
    -0.38
    Plural
    -0.38
    انيف
    -0.38
    POSITIVE LOGITS
     trading
    1.05
     Trading
    0.95
    trading
    0.90
     market
    0.88
    Trading
    0.87
    wapV
    0.82
     traders
    0.82
     markets
    0.81
     Markets
    0.81
     Market
    0.78
    Activations Density 0.033%

    No Known Activations