© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 13630
    Prev
    Next
    INDEX
    Explanations

    specific references to spices and peppers in food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     close
    -0.88
     Close
    -0.82
    Close
    -0.76
     closeness
    -0.75
    close
    -0.73
     closer
    -0.72
     CLOSE
    -0.65
     Closer
    -0.64
     closest
    -0.61
    CLOSE
    -0.61
    POSITIVE LOGITS
     peppers
    1.15
     pepper
    1.13
     Pepper
    1.04
    🌶
    1.04
     chili
    1.03
     chilli
    1.00
    Pepper
    0.99
     Peppers
    0.96
    pepper
    0.90
     spicy
    0.89
    Activations Density 0.137%

    No Known Activations