Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105177
    Prev
    Next
    INDEX
    Explanations

    references to the sea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     contribution
    -0.49
    anting
    -0.49
    endroit
    -0.47
    lllllllll
    -0.46
    ons
    -0.46
    menter
    -0.45
     Pritchard
    -0.44
    amientos
    -0.43
    ugget
    -0.43
    tift
    -0.43
    POSITIVE LOGITS
    Sea
    1.06
     Sea
    1.02
     sea
    0.98
     SEA
    0.90
    sea
    0.80
     seawater
    0.77
     Seas
    0.77
     seabed
    0.76
    SEA
    0.75
     Seaman
    0.75
    Activations Density 0.007%

    No Known Activations