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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113677
    Prev
    Next
    INDEX
    Explanations

    references to candy, particularly candy corn and its manufacturers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     nahilalakip
    -0.65
    enderror
    -0.62
     ujednoznacz
    -0.61
    bootstrapcdn
    -0.61
    ſicht
    -0.60
     deſſen
    -0.59
     erſt
    -0.59
    <pad>
    -0.59
    [@BOS@]
    -0.59
    <unused3>
    -0.59
    POSITIVE LOGITS
     candy
    0.92
     candies
    0.78
    candy
    0.72
    🍬
    0.69
    Candy
    0.68
     Candy
    0.67
    🍭
    0.61
     sweets
    0.57
     confection
    0.56
     Süß
    0.52
    Activations Density 0.012%

    No Known Activations