© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3928
    Prev
    Next
    INDEX
    Explanations

    references to programming, configuration settings, and file structures within code

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

    configuration and code-related syntax tokens involving location, width, size, and coordinates.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     تضيفلها
    -1.03
    Tembelea
    -1.00
    RenderAtEndOf
    -0.97
    AndEndTag
    -0.94
     للمعارف
    -0.93
     autorytatywna
    -0.93
    TagMode
    -0.91
     صوتيه
    -0.91
     ſeine
    -0.89
     faſt
    -0.89
    POSITIVE LOGITS
     and
    0.44
     or
    0.35
     plus
    0.35
     +
    0.32
    ようです
    0.31
     Wissenschaften
    0.28
    ufnahme
    0.28
     as
    0.27
     while
    0.27
    if
    0.27
    Activations Density 0.970%

    No Known Activations