© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2982
    Prev
    Next
    INDEX
    Explanations

    terms related to seafood, particularly various types of crustaceans and seafood dishes

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

    Seafood: crab, lobster, prawns

    np_acts-logits-general · gemini-2.0-flash

    crabs, shrimp, and lobster

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.36
     VET
    -0.33
     OB
    -0.32
    fontName
    -0.32
     Callaway
    -0.31
     VM
    -0.31
     silo
    -0.31
    justifyContent
    -0.30
     BD
    -0.30
     SDG
    -0.30
    POSITIVE LOGITS
     Crab
    1.02
    Crab
    1.00
     crab
    1.00
     crabs
    0.98
     Shrimp
    0.96
     lobster
    0.94
    crab
    0.93
     lobsters
    0.93
     shrimp
    0.93
    Shrimp
    0.91
    Activations Density 0.227%

    No Known Activations