© 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. 30-GEMMASCOPE-RES-16K
    11. 7608
    Prev
    Next
    INDEX
    Explanations

    programming-related function definitions and variable assignments

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

    "Right" or "bottom" appearing in context

    np_acts-logits-general · gemini-2.0-flash

    bottom right

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     early
    -0.59
     opener
    -0.56
    early
    -0.52
    izophren
    -0.51
     awal
    -0.50
    isFirst
    -0.49
    Early
    -0.49
     prefixes
    -0.49
     earlier
    -0.48
    前半
    -0.48
    POSITIVE LOGITS
     posterior
    0.81
     Posterior
    0.75
    Posterior
    0.73
     posteriorly
    0.73
     late
    0.73
     posteriori
    0.70
    posterior
    0.69
    後
    0.68
    后
    0.66
     akhir
    0.66
    Activations Density 0.952%

    No Known Activations