© 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. 20-GEMMASCOPE-RES-131K
    11. 20470
    Prev
    Next
    INDEX
    Explanations

    references to invoices

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

    invoice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    3
    -0.52
    getD
    -0.44
     Central
    -0.42
    getR
    -0.41
     الأعلى
    -0.41
    Then
    -0.41
    assertThat
    -0.40
    rather
    -0.40
    Inggris
    -0.40
    seemed
    -0.40
    POSITIVE LOGITS
     Invoice
    1.20
     invoice
    1.13
    Invoice
    1.01
    invoice
    0.97
     invoices
    0.94
    Invoices
    0.87
    invoices
    0.84
     Invo
    0.76
     invo
    0.73
     factura
    0.69
    Activations Density 0.005%

    No Known Activations