© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 5148
    Prev
    Next
    INDEX
    Explanations

    references to food items, particularly sandwiches and cheese-related ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.97
    contentLoaded
    -0.72
     дописавши
    -0.65
     bezeichneter
    -0.65
     metron
    -0.64
    +#+
    -0.64
     atrop
    -0.62
    ExtendWith
    -0.62
     rhubarb
    -0.62
     Bradshaw
    -0.61
    POSITIVE LOGITS
     cheese
    0.84
    Cheese
    0.80
     Cheese
    0.76
    cheese
    0.69
     cheeses
    0.66
    🧀
    0.65
     Schur
    0.57
    PerformLayout
    0.55
     melted
    0.54
     Cheddar
    0.52
    Activations Density 0.664%

    No Known Activations