Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 5964
    Prev
    Next
    INDEX
    Explanations

    operations related to reading and writing data, particularly in a programming or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gonic
    -0.70
     autorytatywna
    -0.67
     חיצוניים
    -0.62
    GOTREF
    -0.61
     Stern
    -0.60
     Broncos
    -0.59
    EndGlobalSection
    -0.57
     Clippers
    -0.57
     McCullough
    -0.56
    Bagi
    -0.54
    POSITIVE LOGITS
    Читайте
    0.87
     وتسجيلات
    0.82
    Baca
    0.78
    Архівовано
    0.78
    ientí
    0.77
    ⮕
    0.76
    脚注の使い方
    0.76
     uſed
    0.76
    }]
    
    0.73
     ſmall
    0.72
    Activations Density 0.093%

    No Known Activations