© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4668
    Prev
    Next
    INDEX
    Explanations

    terminology related to online lending and finance services, particularly highlighting the accessibility of financial support for various situations like bad credit

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

    before loan/finance related terms

    np_acts-logits-general · gemini-2.0-flash

    instant credit loans

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    лактика
    -0.55
    WriteAttribute
    -0.53
     ویکی‌پدیا
    -0.50
    Skocz
    -0.50
    isContained
    -0.47
     serons
    -0.46
     disponibilités
    -0.45
    merie
    -0.45
     conten
    -0.44
    AddHtmlAttribute
    -0.44
    POSITIVE LOGITS
     loans
    1.98
     loan
    1.95
     Loans
    1.75
     Loan
    1.68
    Loans
    1.67
     lending
    1.66
     borrowers
    1.65
     borrowing
    1.63
     borrower
    1.62
    loan
    1.56
    Activations Density 0.272%

    No Known Activations