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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12456
    Prev
    Next
    INDEX
    Explanations

    elements related to food, particularly breakfast-related meals and items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nightfall
    -0.57
    UnsafeEnabled
    -0.57
     vinho
    -0.57
    StoryboardSegue
    -0.54
     tonight
    -0.52
    Tonight
    -0.51
     sundown
    -0.49
    thenReturn
    -0.48
     Aires
    -0.48
     kvä
    -0.48
    POSITIVE LOGITS
     breakfast
    1.55
     Breakfast
    1.37
    Breakfast
    1.27
    breakfast
    1.24
     morning
    1.20
     breakfasts
    1.17
     mornings
    1.15
     Morning
    1.06
     eggs
    1.05
     Wake
    1.04
    Activations Density 0.097%

    No Known Activations