© 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. 39-GEMMASCOPE-RES-16K
    11. 2284
    Prev
    Next
    INDEX
    Explanations

    references to food, dietary habits, and their effects on health and well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.66
     imprim
    -0.47
    󠁣
    -0.45
     referenties
    -0.44
     Kese
    -0.42
     vectorielle
    -0.42
    ResponseWriter
    -0.42
    sidemargin
    -0.42
    IndentedString
    -0.41
    resizingMask
    -0.41
    POSITIVE LOGITS
     eating
    2.28
     eat
    2.22
     consume
    1.98
     consuming
    1.98
     eats
    1.97
     consumption
    1.96
     eaten
    1.95
    Eating
    1.81
     Eating
    1.81
    eating
    1.79
    Activations Density 0.727%

    No Known Activations