© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2531
    Prev
    Next
    INDEX
    Explanations

    references to tax-related financial obligations or debts

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

    Financial debt or tax issues

    np_acts-logits-general · gemini-2.0-flash

    money owed or late

    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
    tagHelperRunner
    -0.74
    MigrationBuilder
    -0.74
     NSCoder
    -0.69
     useContext
    -0.61
     makeStyles
    -0.59
    adaptiveStyles
    -0.57
     ProtoMessage
    -0.56
     lubric
    -0.56
    InSection
    -0.55
    XmlType
    -0.53
    POSITIVE LOGITS
     overdue
    1.45
     owed
    1.27
     arrears
    1.24
     unpaid
    1.20
     outstanding
    1.15
     delinquent
    1.14
     bills
    1.12
     owe
    1.05
     bill
    1.04
     owing
    1.03
    Activations Density 0.365%

    No Known Activations