© 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. 35-GEMMASCOPE-RES-16K
    11. 6248
    Prev
    Next
    INDEX
    Explanations

    mentions of farm and garage-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seat
    -0.34
    ßerdem
    -0.34
     çi
    -0.33
     sə
    -0.32
    点点头
    -0.32
     صند
    -0.32
     bày
    -0.32
     seats
    -0.31
     seating
    -0.31
     Seating
    -0.31
    POSITIVE LOGITS
     garage
    1.54
     garages
    1.45
    garage
    1.33
     Garage
    1.27
    Garage
    1.23
     shed
    1.17
     garaje
    1.16
    shed
    1.13
     carport
    1.12
     sheds
    1.11
    Activations Density 0.151%

    No Known Activations