© 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. 36-GEMMASCOPE-RES-16K
    6. 15145
    Prev
    Next
    INDEX
    Explanations

    descriptions and details about food markets and their offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issner
    -0.40
    mitian
    -0.39
    żd
    -0.37
     biblioteca
    -0.35
     Bibliothek
    -0.35
    Bedrooms
    -0.34
    パスタ
    -0.33
    Hotel
    -0.32
     Bedroom
    -0.32
     ujednoznacz
    -0.32
    POSITIVE LOGITS
     vendors
    1.70
     stalls
    1.66
     stall
    1.61
     vendor
    1.59
     Vendors
    1.48
     Vendor
    1.35
    Vendors
    1.34
    vendor
    1.30
     booths
    1.30
     booth
    1.27
    Activations Density 0.216%

    No Known Activations