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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 3404
    Prev
    Next
    INDEX
    Explanations

    mathematical questions and calculations, especially those involving operations or comparisons of values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dennoch
    -0.48
    ier
    -0.45
     Trotzdem
    -0.44
    dcterms
    -0.44
    Nonetheless
    -0.44
    Anyways
    -0.43
    Meski
    -0.43
     LIRE
    -0.42
     meski
    -0.41
     diatas
    -0.41
    POSITIVE LOGITS
     okuyayım
    0.82
     Roskov
    0.81
    enumi
    0.78
     ModelRenderer
    0.74
    featureID
    0.74
    ViewFeatures
    0.73
     Answers
    0.73
    enumii
    0.71
    migrationBuilder
    0.70
    AntiForgeryToken
    0.69
    Activations Density 0.604%

    No Known Activations