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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 15253
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "do" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.90
     agrí
    -0.77
     تضيفلها
    -0.70
    richTextPanel
    -0.70
    ณฑ
    -0.69
     NSCoder
    -0.68
    AppCompatTheme
    -0.68
     Himo
    -0.66
    aarrggbb
    -0.64
     Drapeau
    -0.63
    POSITIVE LOGITS
    do
    1.51
    DO
    1.15
    до
    0.78
     DO
    0.67
    dos
    0.58
     kasarigan
    0.57
    gestone
    0.56
     Odo
    0.55
    ndo
    0.52
    doa
    0.51
    Activations Density 0.112%

    No Known Activations