© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8568
    Prev
    Next
    INDEX
    Explanations

    elements related to baking and dessert preparation

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

    cakes or baking

    np_acts-logits-general · gemini-2.0-flash

    cake and baking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.61
     Mantis
    -0.59
     rurale
    -0.57
    Jeep
    -0.56
     AppCompat
    -0.56
     Chiropractic
    -0.56
     Bras
    -0.54
    ropractic
    -0.54
    Magnetic
    -0.53
     Magnetic
    -0.53
    POSITIVE LOGITS
     cake
    2.08
     cakes
    1.89
     Cake
    1.82
    cake
    1.70
     Cakes
    1.68
    Cake
    1.67
     CAKE
    1.64
     baking
    1.54
     bake
    1.54
    Cakes
    1.47
    Activations Density 0.124%

    No Known Activations