© 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
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12937
    Prev
    Next
    INDEX
    Explanations

    references to financial or legislative documents, specifically bills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.62
    SharedDtor
    -0.50
     autorytatywna
    -0.46
    OGND
    -0.44
    TagMode
    -0.42
    multer
    -0.42
    ViewFeatures
    -0.41
    Whom
    -0.41
     Landlord
    -0.40
    Demografía
    -0.40
    POSITIVE LOGITS
     bill
    0.96
     factor
    0.92
    Factor
    0.88
     Factor
    0.87
    bill
    0.84
     bills
    0.83
     invoice
    0.83
     FACTOR
    0.81
    factor
    0.79
     invoices
    0.76
    Activations Density 0.169%

    No Known Activations