© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13444
    Prev
    Next
    INDEX
    Explanations

    technical terms related to machine learning models and their functionality

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

    Python and machine learning code, particularly related to model training, loading, and prediction operations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Архивировано
    -0.35
     mãe
    -0.35
     Burr
    -0.35
    initData
    -0.35
    kust
    -0.34
     Bur
    -0.34
     Luft
    -0.34
    planung
    -0.33
     вста
    -0.33
     balanced
    -0.33
    POSITIVE LOGITS
     predictions
    0.83
     betweenstory
    0.71
     predict
    0.70
     Predictions
    0.70
     prediction
    0.69
     Predicted
    0.68
     predicted
    0.67
    WebElementEntity
    0.66
     Prediction
    0.63
     predicts
    0.61
    Activations Density 0.340%

    No Known Activations