© 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. 22-GEMMASCOPE-RES-16K
    11. 4177
    Prev
    Next
    INDEX
    Explanations

    information related to epoch, validation, training, and cross-validation processes in machine learning

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

    Training and testing in machine learning

    np_acts-logits-general · gemini-2.0-flash

    training and testing data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LLocation
    -0.50
    ennes
    -0.50
     Femen
    -0.48
    omia
    -0.48
    cisme
    -0.47
    jai
    -0.47
    Према
    -0.46
     Signature
    -0.46
    ני
    -0.46
    ungkan
    -0.46
    POSITIVE LOGITS
     epoch
    0.75
    Epoch
    0.69
    epoch
    0.69
     Epoch
    0.66
     epochs
    0.64
     EPO
    0.61
     patience
    0.59
     scheduler
    0.57
     loss
    0.56
    SBATCH
    0.56
    Activations Density 0.181%

    No Known Activations