© 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. 31-GEMMASCOPE-RES-16K
    11. 2907
    Prev
    Next
    INDEX
    Explanations

    class and object-related constructs in programming code

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

    instantiation of generic or parameterized class/type objects.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    rungsseite
    -0.77
     EconPapers
    -0.64
    TagMode
    -0.63
    Diweddarwch
    -0.63
    تقاوى
    -0.60
    Izvori
    -0.59
    featureID
    -0.59
     AssemblyCulture
    -0.58
    tagHelperRunner
    -0.58
    RetentionPolicy
    -0.58
    POSITIVE LOGITS
    ().
    0.54
    (
    0.52
    ();
    0.49
    (),
    0.46
    ();
    0.43
     ().
    0.41
    (-
    0.39
    ());
    0.39
    ()));
    0.38
     (),
    0.38
    Activations Density 0.092%

    No Known Activations