© 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. 24-GEMMASCOPE-RES-16K
    11. 13758
    Prev
    Next
    INDEX
    Explanations

    references to technology use and its implications for responsible digital citizenship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Digital-related terms or concepts

    np_acts-logits-general · gemini-2.0-flash

    digital technology and internet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.62
    reportWebVitals
    -0.55
     دیکھیے
    -0.55
    BeginContext
    -0.53
    มาะ
    -0.49
     ролях
    -0.49
     MenuView
    -0.48
    ajinan
    -0.48
     Мексичка
    -0.47
    uldade
    -0.47
    POSITIVE LOGITS
     digital
    2.27
     computer
    2.01
     Digital
    1.97
    digital
    1.96
     Internet
    1.93
     internet
    1.92
     digitale
    1.89
    Digital
    1.88
     technology
    1.87
     computers
    1.86
    Activations Density 0.696%

    No Known Activations