© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7706
    Prev
    Next
    INDEX
    Explanations

    references to various types of bills and legislation

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

    "bill"

    np_acts-logits-general · gemini-2.0-flash

    bill and related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Méndez
    -0.54
     Hecht
    -0.49
     동안
    -0.49
     Metzger
    -0.48
     Baumann
    -0.48
    ever
    -0.46
    imedes
    -0.46
    petto
    -0.46
     frequência
    -0.45
     Gonçalves
    -0.45
    POSITIVE LOGITS
     bill
    2.20
     Bill
    2.08
    Bill
    2.06
    bill
    1.93
     bills
    1.82
     BILL
    1.78
    BILL
    1.73
     Bills
    1.72
    bills
    1.58
    Bills
    1.56
    Activations Density 0.095%

    No Known Activations