© 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
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 7250
    Prev
    Next
    INDEX
    Explanations

    phrases related to underwater exploration and marine life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.39
    INCREF
    -0.39
    StructEnd
    -0.38
     geométrico
    -0.38
     cucchiai
    -0.38
    cricket
    -0.38
    avras
    -0.38
    fieurs
    -0.36
    Cricket
    -0.36
     sánh
    -0.36
    POSITIVE LOGITS
     dive
    1.87
     diving
    1.73
     Dive
    1.61
     dives
    1.54
     dived
    1.52
    Dive
    1.49
     diver
    1.48
    dive
    1.47
     divers
    1.46
     Diving
    1.41
    Activations Density 0.219%

    No Known Activations