© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 3529
    Prev
    Next
    INDEX
    Explanations

    terms related to loss functions and performance metrics in machine learning

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

    CNN architecture or training

    np_acts-logits-general · gemini-2.0-flash

    trained CNN

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stewart
    -0.49
     refusé
    -0.47
     sû
    -0.45
     promoción
    -0.44
     dra
    -0.43
     Loch
    -0.43
    gnus
    -0.43
    <?
    
    -0.42
    ág
    -0.42
     balcón
    -0.41
    POSITIVE LOGITS
     jsPsych
    0.99
    :✨
    0.88
     שוליים
    0.77
     Lightboxes
    0.75
    RegressionTest
    0.74
    LookAnd
    0.74
    SequentialGroup
    0.72
     saites
    0.71
     kasarigan
    0.71
    DockStyle
    0.70
    Activations Density 1.258%

    No Known Activations