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. 73662
    Prev
    Next
    INDEX
    Explanations

    terms related to baseball statistics and gameplay

    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
    rungsseite
    -0.78
     AssemblyCulture
    -0.69
     idéia
    -0.68
    expandindo
    -0.68
     transfieras
    -0.68
     Paglinawan
    -0.67
    CloseOperation
    -0.64
     contextLoads
    -0.63
    DeleteBehavior
    -0.63
    ACHUSET
    -0.62
    POSITIVE LOGITS
     late
    0.43
     time
    0.42
    十二
    0.35
     gut
    0.35
    快
    0.35
    十一
    0.34
     medium
    0.34
    ⌚
    0.34
    十五
    0.34
    替
    0.33
    Activations Density 0.002%

    No Known Activations