© 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. 15-GEMMASCOPE-RES-16K
    11. 2559
    Prev
    Next
    INDEX
    Explanations

    relationships or distinctions in contexts related to data handling and algorithmic classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ظرفیت
    -0.41
    dération
    -0.41
    строи
    -0.39
     facili
    -0.39
    usias
    -0.39
     fér
    -0.39
     Dhabi
    -0.39
     deleg
    -0.38
    gesamt
    -0.38
     veget
    -0.38
    POSITIVE LOGITS
    хьтан
    0.94
     defaultstate
    0.87
     שוליים
    0.87
    TemporalType
    0.84
    脚注の使い方
    0.78
     propOrder
    0.77
     nahilalakip
    0.76
    HasForeignKey
    0.74
     متعلقه
    0.73
    تقاوى
    0.72
    Activations Density 0.767%

    No Known Activations