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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53898
    Prev
    Next
    INDEX
    Explanations

    metrics related to sports statistics and player performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    期刊论文
    -0.63
    reportWebVitals
    -0.53
    BeginContext
    -0.52
    NewUrlParser
    -0.50
     Administrativna
    -0.49
    章节错误
    -0.49
    SequentialGroup
    -0.48
    abstractmethod
    -0.48
     Kni
    -0.47
     Mejía
    -0.47
    POSITIVE LOGITS
     CVC
    0.57
     bounties
    0.56
     TDA
    0.55
     TPA
    0.55
     Jérusalem
    0.54
     RDA
    0.54
     Judaism
    0.53
     MTC
    0.52
    uberge
    0.52
     CEST
    0.51
    Activations Density 0.477%

    No Known Activations