© 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. 35-GEMMASCOPE-RES-16K
    6. 6937
    Prev
    Next
    INDEX
    Explanations

    phrases describing delicious food and dining experiences

    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
     fusca
    -0.55
     femei
    -0.53
     rente
    -0.52
     coser
    -0.50
     pegat
    -0.50
     preventivo
    -0.49
     linho
    -0.48
    akaian
    -0.46
     cromado
    -0.46
     leão
    -0.46
    POSITIVE LOGITS
     flavors
    1.07
     tasted
    1.02
     delicious
    1.02
     flavours
    1.01
     tastes
    1.01
     taste
    0.97
     tasting
    0.96
     flavor
    0.95
     savory
    0.94
     flavorful
    0.94
    Activations Density 0.489%

    No Known Activations