© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15849
    Prev
    Next
    INDEX
    Explanations

    programming constructs and variables in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    styleType
    -0.40
     Мексичка
    -0.35
     PIM
    -0.33
     exe
    -0.33
     au
    -0.32
    MessageInfo
    -0.32
    wim
    -0.32
    <bos>
    -0.32
     bá
    -0.30
     Valer
    -0.30
    POSITIVE LOGITS
     Grüsse
    0.60
    majánló
    0.60
     Italij
    0.58
     Komunikasi
    0.57
     cejas
    0.56
     paisagem
    0.56
     coroa
    0.56
     montanha
    0.55
     Lingkungan
    0.54
     carteira
    0.54
    Activations Density 0.641%

    No Known Activations