© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104173
    Prev
    Next
    INDEX
    Explanations

    concepts related to chaos and complexity in systems

    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
     changements
    -0.35
     changes
    -0.33
    glLoad
    -0.30
     nowo
    -0.30
    的变化
    -0.30
     rappro
    -0.30
     diversi
    -0.29
     assets
    -0.29
     Police
    -0.29
     Policía
    -0.29
    POSITIVE LOGITS
    ViewImports
    0.78
    EndContext
    0.69
     typelib
    0.67
    StructEnd
    0.66
    sizeCache
    0.65
    RenderAtEndOf
    0.65
     '{@
    0.65
    writeFieldEnd
    0.64
     صوتيه
    0.64
     cherchés
    0.63
    Activations Density 0.089%

    No Known Activations