© 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. 15511
    Prev
    Next
    INDEX
    Explanations

    phrases indicating authorship or attribution

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

    Following the word "by"

    np_acts-logits-general · gemini-2.0-flash

    by means or agent

    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
     desmotivaciones
    -0.70
     Bewußt
    -0.62
    leſs
    -0.60
     nôtre
    -0.59
     acrylique
    -0.57
    ſem
    -0.55
     basée
    -0.55
     cheminée
    -0.55
     houſe
    -0.54
     tarko
    -0.54
    POSITIVE LOGITS
     means
    0.68
    standers
    0.68
     virtue
    0.65
    stander
    0.61
     către
    0.59
     dint
    0.57
     way
    0.54
    products
    0.51
    stolic
    0.49
     the
    0.49
    Activations Density 0.369%

    No Known Activations