© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 12559
    Prev
    Next
    INDEX
    Explanations

    financial terms related to payments and reimbursements

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

    expenses, allowances, reimbursements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    投
    -0.43
     Sch
    -0.36
     BC
    -0.35
     Hang
    -0.35
     投
    -0.34
     hang
    -0.34
     dés
    -0.34
     Bet
    -0.33
    Consequences
    -0.33
     How
    -0.33
    POSITIVE LOGITS
     initComponents
    0.77
    Παραπομπές
    0.68
    imbursement
    0.63
     allowances
    0.62
     typelib
    0.56
     transfieras
    0.56
    XmlEnum
    0.55
    autoreleasepool
    0.54
     Expense
    0.54
     nakalista
    0.54
    Activations Density 0.084%

    No Known Activations