© 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. 20-GEMMASCOPE-RES-16K
    11. 5480
    Prev
    Next
    INDEX
    Explanations

    code comments and function definitions related to order statuses in a programming context

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

    payments, orders, or invoices

    np_acts-logits-general · gemini-2.0-flash

    ordering and payment details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inobu
    -0.52
    jois
    -0.49
    TargetException
    -0.48
     catapult
    -0.47
    WebVitals
    -0.47
    ếng
    -0.47
    FieldBuilder
    -0.46
    orta
    -0.46
    یا
    -0.45
     portfolios
    -0.45
    POSITIVE LOGITS
     payment
    1.01
     Payment
    0.93
     invoice
    0.92
     Invoice
    0.84
    Payment
    0.83
     bill
    0.83
     receipts
    0.82
    payment
    0.82
     subtotal
    0.82
     billing
    0.82
    Activations Density 0.119%

    No Known Activations