© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-GEMMASCOPE-RES-16K
    11. 6460
    Prev
    Next
    INDEX
    Explanations

    code structures and elements related to method or function definitions in a programming 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
    Попис
    -0.59
     kuhusu
    -0.52
    خة
    -0.52
     wireType
    -0.48
     deschis
    -0.47
     Ucraina
    -0.47
    kloped
    -0.46
     halfway
    -0.46
    Poloha
    -0.46
     població
    -0.45
    POSITIVE LOGITS
     références
    2.38
     שוליים
    2.27
    Lähteet
    2.27
     consultato
    2.18
    Einzelnachweise
    2.17
    Przypisy
    2.16
    原始内容存档于
    2.15
    مصادر
    2.14
     跳转至
    2.14
    Bronnen
    2.12
    Activations Density 0.019%

    No Known Activations