© 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
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 10593
    Prev
    Next
    INDEX
    Explanations

    culinary terms and references to baked goods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.64
    IsMutable
    -0.61
     intStringLen
    -0.58
    oa̍t
    -0.53
    ArrowToggle
    -0.52
     EconPapers
    -0.52
     dAtA
    -0.52
    iNdEx
    -0.51
     كومونز
    -0.50
    __))
    -0.48
    POSITIVE LOGITS
     cake
    0.57
     icing
    0.47
     Cake
    0.44
     gâteau
    0.43
     buttercream
    0.42
     frosting
    0.42
     cakes
    0.42
     CAKE
    0.41
    cake
    0.41
    Cake
    0.40
    Activations Density 0.200%

    No Known Activations