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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6451
    Prev
    Next
    INDEX
    Explanations

    terms related to financial data and balances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     متعلقه
    -0.64
    TintMode
    -0.53
     récomp
    -0.50
     Савезне
    -0.48
    простра
    -0.47
     Pind
    -0.47
    econ
    -0.47
    ftagPool
    -0.46
    neté
    -0.46
    minating
    -0.46
    POSITIVE LOGITS
     reserves
    1.11
     reserve
    1.00
     assets
    0.99
     liquidity
    0.98
     balance
    0.93
     Assets
    0.92
     cash
    0.89
     balances
    0.89
     liabilities
    0.87
     Reserves
    0.86
    Activations Density 0.171%

    No Known Activations