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. 16-GEMMASCOPE-RES-16K
    6. 3037
    Prev
    Next
    INDEX
    Explanations

    syncretic influences between different cultural or religious traditions

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

    Borrowing, incorporating, or picking up elements

    np_acts-logits-general · gemini-2.0-flash

    borrowing elements from others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.65
     armp
    -0.55
    atalos
    -0.53
    はじめに
    -0.51
     fiume
    -0.51
    saraba
    -0.51
    ſelf
    -0.50
    WithEmail
    -0.49
    rungsseite
    -0.49
    出版年
    -0.48
    POSITIVE LOGITS
     borrow
    0.98
     borrowed
    0.92
     incorporate
    0.89
     incorporation
    0.87
     borrowing
    0.87
     elements
    0.85
     incorporated
    0.82
    borrow
    0.81
     incorporating
    0.76
     incorporates
    0.74
    Activations Density 0.408%

    No Known Activations