© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12-GEMMASCOPE-RES-16K
    11. 10764
    Prev
    Next
    INDEX
    Explanations

    specific types of formatting or structure indicators, particularly brackets and symbols associated with code or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )':
    -0.63
    ')))
    -0.62
    )')
    -0.61
     ''),
    -0.61
    ())))
    -0.59
    onOptions
    -0.57
    )');
    -0.57
    gameserver
    -0.56
    >())
    -0.56
    "))
    -0.56
    POSITIVE LOGITS
     [
    1.71
    [
    1.48
    ([
    1.24
    {[
    1.24
     $[
    1.23
     ([
    1.16
    -[
    1.15
    [\
    1.13
     }^{[
    1.13
    ,[
    1.11
    Activations Density 0.659%

    No Known Activations