© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 20-GEMMASCOPE-RES-16K
    11. 6865
    Prev
    Next
    INDEX
    Explanations

    references to specific food items and cooking methods

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

    food and cooking-related terms, particularly ingredients and cooking techniques for meat dishes.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     coger
    -0.36
     plugging
    -0.35
     semillas
    -0.34
     conos
    -0.34
     стакан
    -0.34
    耐
    -0.34
    Vía
    -0.34
     poussière
    -0.33
    Wave
    -0.33
     nubes
    -0.33
    POSITIVE LOGITS
     meat
    1.09
    meat
    0.92
     meats
    0.89
     MEAT
    0.89
     Meat
    0.88
    Meat
    0.88
     beef
    0.79
     Beef
    0.79
     vlees
    0.77
     steaks
    0.75
    Activations Density 0.086%

    No Known Activations