© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5167
    Prev
    Next
    INDEX
    Explanations

    references to documents and document-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Konkurrenz
    -0.62
     popularidad
    -0.58
     voordeel
    -0.57
    lewati
    -0.57
     ennemi
    -0.56
     avantage
    -0.54
     Vorteil
    -0.54
    Avantages
    -0.53
     himſelf
    -0.52
    Kariera
    -0.52
    POSITIVE LOGITS
     Document
    1.72
     document
    1.69
    Document
    1.55
    document
    1.48
     documents
    1.44
     Documents
    1.38
     DOCUMENT
    1.30
    DOCUMENT
    1.25
    documents
    1.21
     dokument
    1.18
    Activations Density 0.081%

    No Known Activations