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

    Neuronpedia

    Jacobian LensNEW
    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. 23-GEMMASCOPE-RES-16K
    11. 10683
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their relationships to establishments or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impracticable
    -0.41
     gestaltet
    -0.37
    urbo
    -0.36
    Corporate
    -0.36
     projekty
    -0.35
    TITUDE
    -0.35
    cso
    -0.34
    ➌
    -0.34
     corporate
    -0.34
     Corporate
    -0.34
    POSITIVE LOGITS
     shop
    0.98
    ร้าน
    0.96
     shops
    0.89
     store
    0.79
     retailer
    0.76
    Shop
    0.76
     Shop
    0.76
     shopkeeper
    0.75
     Shops
    0.73
    shop
    0.73
    Activations Density 0.323%

    No Known Activations