© 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. 4-GEMMASCOPE-RES-16K
    11. 3721
    Prev
    Next
    INDEX
    Explanations

    structured data formats and programming elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ★★★★★
    -0.65
     createContext
    -0.63
    DataAnnotations
    -0.62
    oa̍t
    -0.58
    URIComponent
    -0.58
     ویکی‌پدی
    -0.57
    forth
    -0.56
    涯
    -0.56
    iços
    -0.56
    ⟭
    -0.55
    POSITIVE LOGITS
    судар
    0.57
     الحره
    0.54
    --){
    0.54
    "</
    0.52
     lucru
    0.51
    veston
    0.49
     ciasc
    0.49
     الاطلاع
    0.48
    gapi
    0.48
    nps
    0.47
    Activations Density 0.236%

    No Known Activations