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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 130983
    Prev
    Next
    INDEX
    Explanations

    references to vegetables and vegetarian dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     EconPapers
    -0.65
     ब्रेकडाउन
    -0.58
    verläs
    -0.56
    setContentView
    -0.54
    Билгалдахарш
    -0.53
     resourceCulture
    -0.52
     '\\;'
    -0.49
    UIControlState
    -0.47
    homonymie
    -0.46
     defStyle
    -0.46
    POSITIVE LOGITS
     veggies
    0.71
     vegetables
    0.66
    vegetables
    0.57
     vegetable
    0.53
    vegetable
    0.53
    Vegetables
    0.53
     veggie
    0.52
    野菜
    0.51
     Vegetables
    0.50
     salad
    0.49
    Activations Density 0.015%

    No Known Activations