© 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. 10435
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and symbols relevant to statistical models

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

    LaTeX math mode: _{ and (

    np_acts-logits-general · gemini-2.0-flash

    indices and arithmetic operations

    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
    PRNewswire
    -0.65
    tvguidetime
    -0.53
    propTypes
    -0.52
    ashima
    -0.51
    PositiveButton
    -0.51
     propTypes
    -0.50
    OfYear
    -0.50
    ⓘ
    -0.49
    Projekt
    -0.48
    prnewswire
    -0.48
    POSITIVE LOGITS
    IsMutable
    0.72
     defaultstate
    0.72
     -(
    0.71
    -(
    0.69
    &(
    0.62
    /(
    0.61
    olfen
    0.60
     /(
    0.59
    --(
    0.57
     previous
    0.56
    Activations Density 1.000%

    No Known Activations