© 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. 93506
    Prev
    Next
    INDEX
    Explanations

    various forms of textual quotes in the document

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

    phrases introducing quotes

    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
     M
    -0.52
     Rens
    -0.48
     H
    -0.46
     B
    -0.46
     HM
    -0.45
     S
    -0.45
    -
    -0.45
     (
    -0.44
     Ens
    -0.44
     BM
    -0.44
    POSITIVE LOGITS
     Quote
    1.13
     QUOTE
    1.10
    Quote
    1.08
     quote
    1.02
    quote
    1.01
    Quotation
    0.92
     Quo
    0.91
     quotes
    0.89
     quoting
    0.88
     Quotes
    0.86
    Activations Density 0.008%

    No Known Activations