© 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. 3862
    Prev
    Next
    INDEX
    Explanations

    linguistic structures and concepts related to case marking and grammar

    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
     propOrder
    -0.60
    Geplaatst
    -0.55
    Sklici
    -0.53
     &___
    -0.47
    ViewChild
    -0.47
     ImageIcon
    -0.46
     Scouting
    -0.45
     scouting
    -0.44
    Chham
    -0.44
    AsUp
    -0.44
    POSITIVE LOGITS
    $}}
    0.77
     linguistic
    0.73
     lexical
    0.71
     lingu
    0.70
     linguistique
    0.68
     Leech
    0.67
     Linguistics
    0.67
     speaker
    0.66
     Speakers
    0.66
     Chomsky
    0.66
    Activations Density 0.245%

    No Known Activations