© 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. 22-GEMMASCOPE-RES-16K
    11. 5262
    Prev
    Next
    INDEX
    Explanations

    terms related to performance evaluation metrics in neural network contexts

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

    "Training" or "test" data, often with datasets

    np_acts-logits-general · gemini-2.0-flash

    training and test 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
     calloc
    -0.50
     Kemp
    -0.47
    acos
    -0.45
    SeekBar
    -0.45
    elemField
    -0.45
     propOrder
    -0.45
     interpretation
    -0.45
    //
    -0.44
    HasColumnType
    -0.44
     melted
    -0.44
    POSITIVE LOGITS
     training
    0.97
     train
    0.94
    train
    0.93
     dataset
    0.90
     Training
    0.85
    Train
    0.85
    Training
    0.84
    training
    0.82
    TRAIN
    0.82
     Dataset
    0.82
    Activations Density 0.462%

    No Known Activations