© 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. 40-GEMMASCOPE-RES-16K
    11. 7533
    Prev
    Next
    INDEX
    Explanations

    content related to the impact of the coronavirus pandemic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.53
     mães
    -0.50
     vectorielles
    -0.48
     exportaciones
    -0.46
    fjspx
    -0.44
     alimentaire
    -0.44
    apropri
    -0.43
     armadura
    -0.43
     malade
    -0.42
     commerciaux
    -0.42
    POSITIVE LOGITS
     COVID
    1.25
     Covid
    1.06
    COVID
    0.93
     covid
    0.90
     pandemic
    0.89
     coronavirus
    0.81
    Covid
    0.79
     Corona
    0.77
     corona
    0.77
    covid
    0.76
    Activations Density 0.177%

    No Known Activations