© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 4730
    Prev
    Next
    INDEX
    Explanations

    logging and error handling statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.78
    enderror
    -0.72
     للاسماء
    -0.69
    __(/*!
    -0.65
    rawDesc
    -0.64
    </tfoot>
    -0.63
     CreateTagHelper
    -0.63
    навли
    -0.62
    %";
    -0.61
    RegressionTest
    -0.61
    POSITIVE LOGITS
    Tembelea
    0.52
    XmlType
    0.47
     Constitucional
    0.47
     ExecuteAsync
    0.46
     <",
    0.45
    WithMany
    0.43
     intelligen
    0.42
    spaceBetween
    0.41
    guh
    0.41
    neté
    0.40
    Activations Density 0.089%

    No Known Activations