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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3309
    Prev
    Next
    INDEX
    Explanations

    specific statistics and events related to sports games

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     accelerating
    -0.33
    telor
    -0.31
    บาย
    -0.30
     desc
    -0.29
     rapid
    -0.29
     kệ
    -0.27
     RAP
    -0.27
    DCHECK
    -0.27
     rapidly
    -0.27
     ignored
    -0.26
    POSITIVE LOGITS
    verifyException
    0.75
    contentLoaded
    0.63
     Paglinawan
    0.62
    SharedCtor
    0.60
    setVerticalGroup
    0.57
     introvert
    0.56
     scoreless
    0.55
    Diweddarwch
    0.54
    缓慢
    0.53
     silêncio
    0.52
    Activations Density 0.392%

    No Known Activations