© 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. 16-GEMMASCOPE-RES-16K
    11. 7168
    Prev
    Next
    INDEX
    Explanations

    mentions of recent time periods or studies

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

    "recent" and following words

    np_acts-logits-general · gemini-2.0-flash

    recent work, years, times, questions, weeks, studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بيها
    -0.73
     dalamnya
    -0.70
     uiteindelijk
    -0.66
     siguran
    -0.64
     zich
    -0.63
     bugün
    -0.62
    ıyı
    -0.61
     célè
    -0.61
     kuni
    -0.60
     allerede
    -0.60
    POSITIVE LOGITS
     RECENT
    0.87
    PerformLayout
    0.86
    RECENT
    0.84
    Recent
    0.83
     recent
    0.82
     resourceCulture
    0.82
     Recent
    0.81
     recente
    0.81
    nocache
    0.79
     trends
    0.78
    Activations Density 0.073%

    No Known Activations