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. 16-GEMMASCOPE-RES-16K
    6. 15993
    Prev
    Next
    INDEX
    Explanations

    details related to food and dining experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Outdoor seating or patios

    np_acts-logits-general · gemini-2.0-flash

    outdoor seating and dining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.78
    HasForeignKey
    -0.58
     ويكيميديا
    -0.56
    Hozzáférés
    -0.53
    luiting
    -0.52
    getMenuInflater
    -0.50
    قایناقلار
    -0.50
    ême
    -0.49
    iële
    -0.48
    std
    -0.48
    POSITIVE LOGITS
     OFDb
    0.76
     seating
    0.76
     picnic
    0.73
     Seating
    0.71
     dining
    0.68
     patio
    0.67
     overlooking
    0.66
     Patio
    0.66
     benches
    0.65
     terrace
    0.64
    Activations Density 0.077%

    No Known Activations