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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8871
    Prev
    Next
    INDEX
    Explanations

    references to kitchens and culinary professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.73
    NameInMap
    -0.62
     esternos
    -0.59
    tagHelperRunner
    -0.51
    adpleegd
    -0.47
    Jereo
    -0.46
     otomatig
    -0.45
    الدراسه
    -0.45
     Signalez
    -0.45
     jspb
    -0.44
    POSITIVE LOGITS
     Kitchen
    0.57
     Searching
    0.56
    Kitchen
    0.54
    Searching
    0.54
     kitchen
    0.53
     stoves
    0.52
     cook
    0.51
    CloseOperation
    0.51
     KITCHEN
    0.51
     cooks
    0.50
    Activations Density 0.174%

    No Known Activations