© 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. 20-GEMMASCOPE-RES-16K
    11. 9069
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to structured data and systems

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

    before names or titles

    np_acts-logits-general · gemini-2.0-flash

    technical details followed by specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )__
    -0.53
    reportWebVitals
    -0.52
    }}}}
    -0.50
    ized
    -0.48
     épaules
    -0.48
    ised
    -0.47
     []);
    -0.47
    izeit
    -0.47
     enfans
    -0.47
    "]="
    -0.46
    POSITIVE LOGITS
     AssemblyCompany
    0.92
     للمعارف
    0.87
    étit
    0.86
    uxxxx
    0.86
    ItemBackground
    0.85
    expandindo
    0.81
     AssemblyTitle
    0.79
    ArrowToggle
    0.76
    HasAnnotation
    0.73
    uyasha
    0.72
    Activations Density 4.360%

    No Known Activations