© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1730
    Prev
    Next
    INDEX
    Explanations

    financial terms and language related to trading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndInit
    -0.89
    出版年
    -0.74
    WireFormatLite
    -0.70
    +#+
    -0.70
    SupportActionBar
    -0.69
    TypedDataSet
    -0.68
    apimachinery
    -0.68
    HostException
    -0.67
     &___
    -0.63
    stateProvider
    -0.62
    POSITIVE LOGITS
     trading
    1.19
     trade
    1.09
     Trade
    1.08
     Trading
    1.06
     trades
    1.06
    Trade
    1.05
    Trading
    0.96
    trading
    0.95
    trade
    0.95
    TRADE
    0.95
    Activations Density 0.100%

    No Known Activations