© 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. 20-GEMMASCOPE-RES-16K
    11. 16302
    Prev
    Next
    INDEX
    Explanations

    references to scientific authors and their contributions in academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    References, often in the format "et al."

    np_acts-logits-general · gemini-2.0-flash

    et al

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.94
    contentLoaded
    -0.93
    ItemBackground
    -0.89
    脚注の使い方
    -0.84
     Italijanski
    -0.82
     تضيفلها
    -0.81
     незавершена
    -0.80
     gainera
    -0.78
    buttonBar
    -0.76
     referenties
    -0.76
    POSITIVE LOGITS
    Me
    0.44
    United
    0.44
    AppCompat
    0.44
    ரு
    0.43
    ImageField
    0.43
    putan
    0.42
     United
    0.41
     theater
    0.41
    flink
    0.40
    щу
    0.40
    Activations Density 0.040%

    No Known Activations