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. 20-GEMMASCOPE-RES-16K
    6. 10088
    Prev
    Next
    INDEX
    Explanations

    various forms and references to friendship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    出版年
    -0.85
     Wicidata
    -0.71
    webElementXpaths
    -0.70
    存于互联网档案馆
    -0.70
     CommonModule
    -0.67
    Rhestr
    -0.64
     بيها
    -0.63
     AssemblyTitle
    -0.63
    ën
    -0.62
     تضيفلها
    -0.61
    POSITIVE LOGITS
    ſhip
    0.69
     детства
    0.67
    zoned
    0.67
     Friends
    0.65
    SHIP
    0.62
     FRIENDS
    0.62
    friends
    0.61
     RELATION
    0.61
    consulté
    0.60
    hips
    0.59
    Activations Density 0.085%

    No Known Activations