© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 86453
    Prev
    Next
    INDEX
    Explanations

    references to the name "Watson" and its variations in different contexts

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

    Wat names and places

    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
     endblock
    -0.72
    endregion
    -0.71
    omla
    -0.71
     betweenstory
    -0.68
     ]
    -0.65
    setupUi
    -0.63
     Juneau
    -0.62
    "])
    -0.61
    erunner
    -0.59
     Greensboro
    -0.59
    POSITIVE LOGITS
     Wat
    0.82
    Wat
    0.76
     Watson
    0.72
     wat
    0.72
     WATSON
    0.71
     Watts
    0.70
    wat
    0.69
     WAT
    0.65
     Watt
    0.65
    Watson
    0.62
    Activations Density 0.009%

    No Known Activations