© 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. 30-GEMMASCOPE-RES-16K
    11. 10693
    Prev
    Next
    INDEX
    Explanations

    references to legal and bankruptcy proceedings

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

    Legal or financial contexts involving debt

    np_acts-logits-general · gemini-2.0-flash

    bankruptcy and insolvency filings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.47
     nahilalakip
    -0.45
     tick
    -0.41
    новниш
    -0.38
     Tick
    -0.38
     bore
    -0.38
    utilisons
    -0.36
     steamed
    -0.36
     ticks
    -0.36
     Booking
    -0.36
    POSITIVE LOGITS
     bankruptcy
    1.30
     Bankruptcy
    1.21
     creditors
    1.17
     bankrupt
    1.04
     insolvency
    1.02
     insolvent
    0.98
     creditor
    0.94
     Insol
    0.92
     debtor
    0.92
     Gläub
    0.86
    Activations Density 0.411%

    No Known Activations