© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84664
    Prev
    Next
    INDEX
    Explanations

    references to sailing and related activities

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

    nautical travel and ships

    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
     Grossman
    -0.47
    <
    -0.45
    k
    -0.44
    3
    -0.44
     Maximus
    -0.43
     Maddox
    -0.42
     Potts
    -0.42
     Muñoz
    -0.42
     Motta
    -0.42
     Muk
    -0.42
    POSITIVE LOGITS
     Sail
    1.14
    Sail
    1.14
     sailing
    1.09
     Sailing
    1.09
     sail
    1.07
     SAIL
    1.07
    sail
    1.02
    sailing
    0.99
    Sailing
    0.99
     sailboat
    0.94
    Activations Density 0.003%

    No Known Activations