© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-131K
    11. 71208
    Prev
    Next
    INDEX
    Explanations

    phrases related to reimbursement and associated expenses

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

    reimbursement of expenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.37
    ectady
    -0.37
    nestjs
    -0.36
     générations
    -0.34
     manio
    -0.34
    roquia
    -0.33
    tagHelperRunner
    -0.32
    SequentialGroup
    -0.31
    لينكات
    -0.30
     cartera
    -0.29
    POSITIVE LOGITS
     reimbursement
    1.52
     reimburse
    1.45
     reimbursed
    1.41
     reimbur
    1.35
     expenses
    1.33
     expense
    1.33
     Expense
    1.31
     Expenses
    1.30
    Expenses
    1.22
    Expense
    1.18
    Activations Density 0.071%

    No Known Activations