© 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. 33-GEMMASCOPE-RES-16K
    11. 14605
    Prev
    Next
    INDEX
    Explanations

    mention of prior studies and research findings related to biomedical topics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    GEBURTSDATUM
    -0.74
    UnusedPrivate
    -0.55
     '\\;'
    -0.54
    Искәрмәләр
    -0.46
    MigrationBuilder
    -0.44
    WebElementEntity
    -0.43
    Зноскі
    -0.42
    ChildScrollView
    -0.41
    bitField
    -0.40
    Externí
    -0.38
    POSITIVE LOGITS
     published
    1.19
     studies
    1.17
     literature
    1.15
     reported
    1.12
     recent
    1.06
     publications
    1.05
    published
    1.04
    studies
    1.02
     recently
    1.01
    reported
    1.01
    Activations Density 2.888%

    No Known Activations