© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 5677
    Prev
    Next
    INDEX
    Explanations

    information related to medicinal properties and uses of plants and natural compounds

    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
     zakup
    -0.35
     barro
    -0.32
     lemn
    -0.31
    MessageOf
    -0.29
    arXiv
    -0.29
     capuz
    -0.29
    */;
    -0.29
    unea
    -0.29
     dimiliki
    -0.29
     doppia
    -0.28
    POSITIVE LOGITS
     industrial
    0.86
     cosmetics
    0.80
    industrial
    0.80
     cosmetic
    0.77
     Industrial
    0.77
     decorative
    0.72
    Industrial
    0.72
     industri
    0.72
     industries
    0.71
     cosmé
    0.71
    Activations Density 0.987%

    No Known Activations