© 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. 18-GEMMASCOPE-RES-16K
    11. 15037
    Prev
    Next
    INDEX
    Explanations

    references to machine learning techniques related to feature extraction and training methodologies

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

    "training" or "test" tokens and data sets

    np_acts-logits-general · gemini-2.0-flash

    train and test data ratios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CAUSE
    -0.53
    WriteLiteral
    -0.52
    Cause
    -0.49
     Cause
    -0.48
    //
    -0.47
    Naissance
    -0.46
     CAUSE
    -0.45
    jspx
    -0.45
    려
    -0.45
     ссылке
    -0.45
    POSITIVE LOGITS
     training
    1.05
    Training
    0.93
     Training
    0.91
     trainer
    0.87
     DataLoader
    0.84
    training
    0.84
     TRAINING
    0.83
     train
    0.80
     trainers
    0.79
     TRAIN
    0.78
    Activations Density 0.393%

    No Known Activations