© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5651
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to loading and saving machine learning models

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

    Refers to training or using trained models

    np_acts-logits-general · gemini-2.0-flash

    neural network training

    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
     STEWART
    -0.52
    SourceChecksum
    -0.51
     reunião
    -0.51
     secco
    -0.48
     collègues
    -0.48
    orianCalendar
    -0.48
    timbangan
    -0.47
     outlaw
    -0.47
     refusé
    -0.47
     schermo
    -0.47
    POSITIVE LOGITS
     training
    1.18
     trained
    1.18
    trained
    1.01
    Training
    0.97
    train
    0.97
     Trained
    0.97
     train
    0.97
    training
    0.97
     Training
    0.96
    Train
    0.92
    Activations Density 1.165%

    No Known Activations