© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15332
    Prev
    Next
    INDEX
    Explanations

    keywords related to debt and financial transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     naudoti
    -0.43
     przypad
    -0.42
    InSection
    -0.41
     būti
    -0.39
     capucha
    -0.39
     spécifique
    -0.38
    Література
    -0.38
    améli
    -0.37
     abuelo
    -0.37
     everywhere
    -0.37
    POSITIVE LOGITS
     repayment
    0.78
     repayments
    0.69
    Mortgage
    0.63
     repaid
    0.62
     Mortgage
    0.62
     Monthly
    0.61
     repay
    0.61
     monthly
    0.59
     actionPerformed
    0.59
     للمعارف
    0.58
    Activations Density 0.331%

    No Known Activations