© 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. 8640
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to scientific publications

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

    the number "4"

    np_acts-logits-general · gemini-2.0-flash

    4 or 4chan

    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
    %)$
    -1.00
    ValueStyle
    -0.78
     وتسجيلات
    -0.76
     Wirt
    -0.72
    شهاد
    -0.72
    jsdelivr
    -0.70
    GOTREF
    -0.70
    hhhhhhhh
    -0.70
    ajevo
    -0.68
    cional
    -0.68
    POSITIVE LOGITS
    4
    1.10
     @"/
    1.05
    fifths
    0.84
    5
    0.80
     Gospels
    0.78
     corners
    0.74
     Corners
    0.73
     paws
    0.73
     Fournier
    0.72
     quadrant
    0.70
    Activations Density 0.990%

    No Known Activations