© 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. 4656
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to art, culture, and community events

    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
     définiti
    -1.07
     commerciaux
    -1.04
     déchir
    -1.01
     vérit
    -0.99
     réfugi
    -0.94
     enfans
    -0.92
     hâte
    -0.92
     commerciales
    -0.91
     extérieurs
    -0.90
     financières
    -0.89
    POSITIVE LOGITS
     programme
    0.70
    -
    0.66
    ´
    0.65
     (=
    0.60
     sector
    0.59
     («
    0.58
     „
    0.56
     programmes
    0.55
     «
    0.55
     (!)
    0.55
    Activations Density 0.574%

    No Known Activations