© 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. 11213
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that pose questions or involve dialogue

    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
     transfieras
    -0.64
    MigrationBuilder
    -0.57
     AssemblyTitle
    -0.56
    reportWebVitals
    -0.56
    TokenNameLBRACE
    -0.54
    <unused94>
    -0.54
    NameInMap
    -0.54
     fashiola
    -0.54
    <unused42>
    -0.54
    <pad>
    -0.53
    POSITIVE LOGITS
    ณ์
    0.35
    Then
    0.35
     then
    0.34
     Then
    0.33
     alors
    0.31
     entonces
    0.31
    дости
    0.31
    HasAnnotation
    0.29
     Entonces
    0.29
    例文帳に追加
    0.29
    Activations Density 0.293%

    No Known Activations