© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12456
    Prev
    Next
    INDEX
    Explanations

    references to breakfast foods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Breakfast or related food

    np_acts-logits-general · gemini-2.0-flash

    breakfast eating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XIM
    -0.53
     الأحمر
    -0.51
    eamiento
    -0.49
    บรร
    -0.48
     Ehrlich
    -0.48
     Wine
    -0.48
     wine
    -0.47
    UnsafeEnabled
    -0.45
    Wine
    -0.44
     vinho
    -0.44
    POSITIVE LOGITS
     breakfast
    1.40
     Breakfast
    1.21
     pancakes
    1.16
    breakfast
    1.13
    Breakfast
    1.11
     breakfasts
    1.06
     Eggs
    1.03
     eggs
    1.03
     desayuno
    1.01
     pancake
    1.00
    Activations Density 0.076%

    No Known Activations