© 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. 6-GEMMASCOPE-RES-16K
    6. 3781
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "await."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    зывы
    -0.57
    p
    -0.54
    ,
    -0.54
    rrggbb
    -0.52
     (
    -0.52
     haar
    -0.52
     p
    -0.49
     window
    -0.49
     ver
    -0.49
    ver
    -0.47
    POSITIVE LOGITS
    await
    2.14
     await
    1.03
     ſta
    0.93
     تضيفلها
    0.92
     Majefty
    0.92
     étoient
    0.89
     avoient
    0.88
    Await
    0.88
    antMatchers
    0.87
     ſtate
    0.86
    Activations Density 0.015%

    No Known Activations