© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 13-GEMMASCOPE-RES-16K
    11. 9139
    Prev
    Next
    INDEX
    Explanations

    instances of the word "do" and its variations, indicating a focus on actions or questions related to doing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    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
    -0.93
     itſelf
    -0.85
     Мексичка
    -0.77
     ...]
    -0.77
     ***!
    -0.72
    ttino
    -0.71
    ſelf
    -0.71
    )}.
    -0.71
     Spani
    -0.71
    hiers
    -0.70
    POSITIVE LOGITS
     do
    1.44
     Do
    1.43
    Do
    1.41
     DO
    1.30
    do
    1.07
    DO
    1.06
     done
    1.01
     does
    0.94
     Does
    0.92
     Dolores
    0.89
    Activations Density 0.159%

    No Known Activations