Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10190
    Prev
    Next
    INDEX
    Explanations

    references to food and recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diisi
    -0.46
     chevaux
    -0.44
     MusicBrainz
    -0.44
    rotum
    -0.43
    noid
    -0.43
    censo
    -0.43
     dipasang
    -0.42
     виправивши
    -0.42
    akov
    -0.42
    cein
    -0.41
    POSITIVE LOGITS
     recipe
    2.01
     recipes
    1.96
    recipe
    1.62
     Recipe
    1.61
     Recipes
    1.59
    recipes
    1.51
    Recipe
    1.47
     RECIPE
    1.44
    Recipes
    1.42
     RECIPES
    1.35
    Activations Density 0.179%

    No Known Activations