© 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. 10-GEMMASCOPE-RES-16K
    11. 8805
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to food and nutrition, including varieties, sources, and related societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abandonné
    -0.88
     amethyst
    -0.87
     verle
    -0.86
     cister
    -0.85
    }`}>
    -0.84
     Prologue
    -0.83
    trise
    -0.83
     AssemblyCompany
    -0.82
     ]);
    -0.81
    __]
    -0.80
    POSITIVE LOGITS
     food
    1.55
     Food
    1.43
     FOOD
    1.30
    food
    1.30
    FOOD
    1.26
     foods
    1.24
    Food
    1.23
     Foods
    1.11
    foods
    1.05
    Foods
    0.94
    Activations Density 0.030%

    No Known Activations