© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 11712
    Prev
    Next
    INDEX
    Explanations

    questions and phrases related to medical treatment and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.58
    AccessorTable
    -0.46
    vician
    -0.41
    VersionUID
    -0.41
    rungsseite
    -0.41
     ComVisible
    -0.40
    Xna
    -0.38
    bigoplus
    -0.38
    ficulties
    -0.36
    Derbyniad
    -0.36
    POSITIVE LOGITS
     last
    4.00
    last
    3.33
     último
    3.02
    Last
    3.00
     Last
    2.94
     última
    2.94
     terakhir
    2.91
     LAST
    2.89
     dernière
    2.89
     dernier
    2.84
    Activations Density 1.710%

    No Known Activations