© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3313
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and debt

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

    Financial lending, debt, and repayment

    np_acts-logits-general · gemini-2.0-flash

    money lent or owed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ритори
    -0.40
    enumi
    -0.35
     prévoir
    -0.33
    viti
    -0.33
    gridy
    -0.33
     dimensioni
    -0.33
    copus
    -0.32
     Sun
    -0.32
     etkili
    -0.32
     News
    -0.31
    POSITIVE LOGITS
    Autoritní
    0.66
     мәкал
    0.65
     lender
    0.60
    Loan
    0.59
     Lending
    0.57
    Debt
    0.57
     loan
    0.57
     Loans
    0.56
     Normdatei
    0.56
     esternos
    0.55
    Activations Density 0.143%

    No Known Activations