© 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 - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8450
    Prev
    Next
    INDEX
    Explanations

    queries about stock valuation and dividends

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

    questions that ask for a computed financial quantity for a stock (e.g., intrinsic value, price, yield, or return), typically framed as “what is/calculate” with growth/required return and percentages.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.71
     tartalomajánló
    -0.62
    onViewCreated
    -0.60
     initComponents
    -0.58
    UseVisualStyle
    -0.57
    NameInMap
    -0.56
    MLLoader
    -0.55
     AssemblyProduct
    -0.55
     somehow
    -0.54
     незавершена
    -0.54
    POSITIVE LOGITS
     '\\;'
    0.63
    dymo
    0.60
    djangoproject
    0.58
    nemia
    0.54
    Assistance
    0.54
    thulhu
    0.53
    culate
    0.52
    र्य
    0.52
    forChild
    0.52
    bells
    0.52
    Activations Density 0.549%

    No Known Activations