Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15622
    Prev
    Next
    INDEX
    Explanations

    references to breakfast-related food items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spass
    -0.40
     насељу
    -0.39
     Purse
    -0.38
     res
    -0.37
     Wine
    -0.35
     autorytatywna
    -0.35
     identidade
    -0.34
    AppCompat
    -0.34
     Relief
    -0.34
     Lime
    -0.34
    POSITIVE LOGITS
     breakfast
    1.71
    Breakfast
    1.53
     Breakfast
    1.52
    breakfast
    1.52
     breakfasts
    1.45
     morning
    1.39
     desayuno
    1.28
    morning
    1.23
     desay
    1.22
     mornings
    1.21
    Activations Density 0.286%

    No Known Activations