© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 4721
    Prev
    Next
    INDEX
    Explanations

    culinary instructions or components related to recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
    ⓧ
    -0.85
    NameInMap
    -0.79
    ArgsConstructor
    -0.70
    ">//
    -0.64
     nahilalakip
    -0.63
     الرياضيه
    -0.62
     المعرف
    -0.62
    RenderAtEndOf
    -0.62
    NewUrlParser
    -0.61
    RegressionTest
    -0.61
    POSITIVE LOGITS
     aggiungere
    0.51
    esgue
    0.50
    belongsTo
    0.49
     socc
    0.49
     toppings
    0.49
    Vorlage
    0.49
     Zacks
    0.47
     cab
    0.46
     bot
    0.43
     freshness
    0.43
    Activations Density 0.120%

    No Known Activations