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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1518
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming functions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -0.30
     most
    -0.29
      
    -0.29
    而来
    -0.29
     is
    -0.29
     era
    -0.28
     are
    -0.27
     as
    -0.26
     dessutom
    -0.26
     many
    -0.25
    POSITIVE LOGITS
    دانشنامهٔ
    0.96
     propOrder
    0.93
     ویکی‌پدی
    0.87
     للمعارف
    0.85
     wikipagina
    0.83
     nahilalakip
    0.82
    IndentedString
    0.82
    лтамалар
    0.81
     sumpay
    0.81
    contentLoaded
    0.81
    Activations Density 0.612%

    No Known Activations