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. 13187
    Prev
    Next
    INDEX
    Explanations

    information about professional athletes, specifically their roles and backgrounds in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     ympä
    -0.64
     мѣ
    -0.59
     tarko
    -0.57
     eikä
    -0.51
     surround
    -0.50
    InputBorder
    -0.49
     personalizada
    -0.46
     surrounding
    -0.46
    yaf
    -0.45
    Rüyada
    -0.45
    POSITIVE LOGITS
    SourceChecksum
    0.80
    ScopeManager
    0.77
     CreateTagHelper
    0.63
    MessageOf
    0.63
    ίος
    0.61
     clearColor
    0.59
    UniformLocation
    0.59
    rungsseite
    0.58
     Pian
    0.56
     born
    0.55
    Activations Density 0.255%

    No Known Activations