© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 11805
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax elements, particularly those that denote code structure or control flow

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Code and math-heavy text

    np_acts-logits-general · gemini-2.0-flash

    (); ** 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     $_"
    -0.75
     $_(
    -0.67
    RegressionTest
    -0.65
     $_[
    -0.63
    ']=='
    -0.60
     ""}
    -0.60
    {?>
    -0.59
    ">
    -0.58
    providedIn
    -0.58
     StatefulWidget
    -0.58
    POSITIVE LOGITS
     الحره
    0.34
     térmica
    0.32
     pä
    0.32
    Because
    0.31
    According
    0.31
     They
    0.31
    because
    0.31
     Because
    0.30
     sociedade
    0.30
     According
    0.30
    Activations Density 0.146%

    No Known Activations