© 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. 21-GEMMASCOPE-RES-16K
    11. 231
    Prev
    Next
    INDEX
    Explanations

    kitchen-related actions and instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.59
    getOutputStream
    -0.50
     Compilation
    -0.48
    quiao
    -0.48
     Berufs
    -0.47
     Carp
    -0.47
     onOptions
    -0.47
    flame
    -0.47
    wol
    -0.46
    carat
    -0.45
    POSITIVE LOGITS
     refrigerator
    1.25
     refrigerate
    1.24
     refrigerated
    1.24
     fridge
    1.18
     freezer
    1.14
     refrigeration
    1.13
     Refrigerator
    1.07
    refriger
    1.05
     refriger
    1.00
     stored
    1.00
    Activations Density 0.155%

    No Known Activations