© 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. 1-GEMMASCOPE-RES-16K
    11. 5461
    Prev
    Next
    INDEX
    Explanations

    words that pertain to legal, medical, or scientific roles and actions, particularly those ending in "ator."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cherchés
    -0.43
     Warne
    -0.42
     Maddie
    -0.37
     chronique
    -0.36
     Marche
    -0.36
    Collegamenti
    -0.36
    咪
    -0.35
    TIMER
    -0.35
    IRMED
    -0.35
     mé
    -0.34
    POSITIVE LOGITS
    ator
    1.88
    ATOR
    1.72
    tor
    1.71
    ctor
    1.70
    itor
    1.63
    TOR
    1.50
    ators
    1.47
    utor
    1.46
    ITOR
    1.45
    etor
    1.45
    Activations Density 0.327%

    No Known Activations