© 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. 10-GEMMASCOPE-RES-16K
    11. 14889
    Prev
    Next
    INDEX
    Explanations

    references to loans and lending activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.59
    makeConstraints
    -0.57
    oneofs
    -0.51
     internetowa
    -0.50
    bitset
    -0.50
     fieldNum
    -0.50
     néz
    -0.49
     صوتيه
    -0.48
    Rhestr
    -0.48
    Aktualisiert
    -0.48
    POSITIVE LOGITS
     loan
    1.68
     Loan
    1.55
    Loan
    1.51
     loans
    1.41
     borrow
    1.41
    loan
    1.38
    Borrow
    1.35
     borrowing
    1.34
     borrowed
    1.34
     Borrow
    1.33
    Activations Density 0.166%

    No Known Activations