© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 7685
    Prev
    Next
    INDEX
    Explanations

    questions that start with "Do"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.87
     Мексичка
    -0.77
    ệm
    -0.71
    ่าง
    -0.70
    )\}
    -0.69
    жидан
    -0.67
     Kamer
    -0.65
     Vij
    -0.65
     Pied
    -0.65
     Kers
    -0.65
    POSITIVE LOGITS
     DO
    1.15
    Do
    1.12
     do
    1.11
     Do
    1.10
    DO
    0.88
    protoimpl
    0.88
     Dov
    0.86
     Dolores
    0.83
    do
    0.83
     Dois
    0.81
    Activations Density 0.064%

    No Known Activations