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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 69518
    Prev
    Next
    INDEX
    Explanations

    references to mollusks and similar marine creatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     jScrollPane
    -0.72
    RoutingModule
    -0.68
    loroethane
    -0.57
     Karo
    -0.56
    ernalia
    -0.56
     jLabel
    -0.55
    typeparam
    -0.55
    RemoveField
    -0.54
    ilight
    -0.53
    PostExecute
    -0.53
    POSITIVE LOGITS
     oyster
    0.75
     oysters
    0.75
     shellfish
    0.73
     Oyster
    0.70
     mussels
    0.57
     mussel
    0.55
     mollus
    0.54
     seafood
    0.52
     clams
    0.50
    🐚
    0.50
    Activations Density 0.015%

    No Known Activations