© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12492
    Prev
    Next
    INDEX
    Explanations

    legal terms related to financial transactions and lending practices

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

    before "loan" or "credit"

    np_acts-logits-general · gemini-2.0-flash

    loan and credit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Skocz
    -0.60
    Académie
    -0.49
    лактика
    -0.48
    WriteAttribute
    -0.46
    cises
    -0.42
    enderror
    -0.42
    ίδι
    -0.42
    Portail
    -0.42
    fromCharCode
    -0.41
    Editora
    -0.41
    POSITIVE LOGITS
     loan
    2.46
     loans
    2.35
     Loan
    2.14
     Loans
    2.08
     lending
    2.03
    loan
    2.00
    Loan
    1.99
     borrowing
    1.96
    Loans
    1.93
     LOAN
    1.88
    Activations Density 0.320%

    No Known Activations