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

    Neuronpedia

    Jacobian LensNEW
    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. 8812
    Prev
    Next
    INDEX
    Explanations

    references to statistical models and their components

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

    Preceding "each"

    np_acts-logits-general · gemini-2.0-flash

    for each

    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
    ThemeOverlay
    -0.80
    StackNavigator
    -0.75
    awakeFromNib
    -0.61
    UserScript
    -0.61
    elseif
    -0.61
     <=",
    -0.60
     SwitchCompat
    -0.60
     للمعارف
    -0.57
    pexpr
    -0.55
    TagMode
    -0.55
    POSITIVE LOGITS
     each
    4.39
    each
    3.65
    Each
    3.57
     Each
    3.53
     EACH
    3.10
     chaque
    2.97
    EACH
    2.92
     fiecare
    2.69
     every
    2.64
    每个
    2.62
    Activations Density 1.819%

    No Known Activations