© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12700
    Prev
    Next
    INDEX
    Explanations

    terms related to monitoring and tracking in educational and technological contexts

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

    Tracking or monitoring activity

    np_acts-logits-general · gemini-2.0-flash

    tracking progress and changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.56
     helft
    -0.49
    المصادر
    -0.40
     verder
    -0.40
    Enllaços
    -0.40
     TextAppearance
    -0.39
    DialogContent
    -0.39
    uyez
    -0.38
    立て
    -0.38
    ought
    -0.38
    POSITIVE LOGITS
     progress
    1.05
     movements
    0.88
     trends
    0.78
     changes
    0.77
     whereabouts
    0.75
    progress
    0.72
     movement
    0.70
     activity
    0.69
     progreso
    0.67
     progression
    0.66
    Activations Density 0.970%

    No Known Activations