© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 2639
    Prev
    Next
    INDEX
    Explanations

    opening and closing code blocks or structures in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.73
    writeField
    -0.69
    httphttps
    -0.68
    省市镇
    -0.62
    ----</
    -0.60
     imageNamed
    -0.55
    出版年
    -0.54
    ullan
    -0.53
    */
    -0.53
    >{@
    -0.52
    POSITIVE LOGITS
     виправивши
    0.73
    ↵
    0.69
     kasarigan
    0.68
     المعيارى
    0.67
     дописавши
    0.66
     חיצוניים
    0.57
    featureID
    0.54
    ViewFeatures
    0.52
    مصادر
    0.51
    BeginContext
    0.51
    Activations Density 0.015%

    No Known Activations