© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 14932
    Prev
    Next
    INDEX
    Explanations

    references to baked goods and desserts

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

    baking

    np_acts-logits-general · gemini-2.0-flash

    bake and cakes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.65
    POOL
    -0.63
    PostInfinity
    -0.62
    pool
    -0.56
    لفل
    -0.56
     indios
    -0.56
    BeforeAll
    -0.56
     Massage
    -0.55
    Več
    -0.54
    Pool
    -0.54
    POSITIVE LOGITS
     bake
    1.58
     baking
    1.56
     cakes
    1.55
     cake
    1.50
     bakery
    1.46
     bakers
    1.44
     baked
    1.43
     baker
    1.43
     Cakes
    1.38
     Bake
    1.31
    Activations Density 0.124%

    No Known Activations