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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-GEMMASCOPE-RES-16K
    6. 12829
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that describe unique or original experiences and products, particularly related to food, accommodations, and design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=",
    -0.69
    harusnya
    -0.67
    ArrowToggle
    -0.66
     незавершена
    -0.64
    PerformLayout
    -0.64
    ISupport
    -0.63
    Espèce
    -0.63
     '\\;'
    -0.61
     فريبيس
    -0.61
    SharedCtor
    -0.60
    POSITIVE LOGITS
     miniature
    0.61
     ingenious
    0.61
     bizarre
    0.59
     unik
    0.58
     unconventional
    0.58
     unusual
    0.58
     unique
    0.57
     shaped
    0.57
     edible
    0.56
     upside
    0.56
    Activations Density 0.401%

    No Known Activations