© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102648
    Prev
    Next
    INDEX
    Explanations

    terms related to biology and medical research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mile
    -0.38
     used
    -0.37
     küche
    -0.36
    (
    -0.35
    Used
    -0.35
     flex
    -0.34
    used
    -0.34
     MILE
    -0.33
     را
    -0.33
     vorbe
    -0.32
    POSITIVE LOGITS
    DataAnnotations
    6.31
     defaultstate
    0.88
     AssemblyCulture
    0.87
    AntiForgeryToken
    0.86
    IntoConstraints
    0.85
    ValueStyle
    0.84
    ModelSerializer
    0.82
     InputDecoration
    0.81
    CppMethod
    0.80
    MigrationBuilder
    0.80
    Activations Density 0.000%

    No Known Activations