Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8273
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to bankruptcy proceedings

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

    Bankruptcy proceedings and insolvency

    np_acts-logits-general · gemini-2.0-flash

    Chapter XI bankruptcy proceedings

    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
     Smarty
    -0.58
     endothelial
    -0.53
    othelial
    -0.53
     resourceCulture
    -0.52
     espor
    -0.52
    reactstrap
    -0.51
     hiperten
    -0.51
    ymce
    -0.50
    ništ
    -0.50
    switch
    -0.50
    POSITIVE LOGITS
     bankruptcy
    1.25
     creditors
    1.13
     Bankruptcy
    1.12
     insolvency
    1.06
     debtor
    1.04
     debtors
    1.00
     Chapter
    0.99
     liquidation
    0.98
     creditor
    0.95
     bankrupt
    0.94
    Activations Density 0.358%

    No Known Activations