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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 2599
    Prev
    Next
    INDEX
    Explanations

    references to ancient Egyptian context and culture

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

    Egypt or Egyptian culture

    np_acts-logits-general · gemini-2.0-flash

    Egypt or Egyptian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocin
    -0.51
    bootstrapcdn
    -0.49
     quim
    -0.48
    lugin
    -0.47
     Stump
    -0.47
     Ashland
    -0.47
     stumps
    -0.46
     Asturias
    -0.46
    Relacion
    -0.45
    coch
    -0.44
    POSITIVE LOGITS
     Egypt
    1.60
     Egyptian
    1.59
    Egypt
    1.44
    Egyptian
    1.42
     EGYPT
    1.40
     Cairo
    1.40
     Egyptians
    1.38
     egip
    1.33
     Egipto
    1.27
     Egy
    1.27
    Activations Density 0.055%

    No Known Activations