© 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. 20-GEMMASCOPE-RES-16K
    11. 6181
    Prev
    Next
    INDEX
    Explanations

    financial obligations, specifically related to taxes

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

    mentions of unpaid taxes, tax liabilities, and IRS (Internal Revenue Service) financial issues.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    references to unpaid financial obligations, especially tax liabilities and collections such as debts owed, balances due, liens, and payment/default status.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    financial obligations and debts owed.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    wide
    -0.33
    er
    -0.32
    innerWidth
    -0.30
    bier
    -0.30
     guided
    -0.29
     Paglinawan
    -0.28
    est
    -0.28
    s
    -0.28
     thế
    -0.28
     Vor
    -0.27
    POSITIVE LOGITS
     payments
    0.81
     payment
    0.76
     arrears
    0.75
     invoices
    0.71
    payments
    0.69
     owed
    0.68
    ロウィン
    0.68
    -------------</
    0.68
     المعيارى
    0.67
     Payment
    0.66
    Activations Density 0.187%

    No Known Activations