© 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. 24-GEMMASCOPE-RES-16K
    11. 7590
    Prev
    Next
    INDEX
    Explanations

    references to the root mean square error in the context of neural networks

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

    training, testing, and data sets

    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 @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.57
     uska
    -0.55
    دانشنامهٔ
    -0.53
    endcsname
    -0.53
    ScopeManager
    -0.53
    MigrationBuilder
    -0.52
    soort
    -0.51
     Installed
    -0.49
    CAUSE
    -0.49
     gescha
    -0.49
    POSITIVE LOGITS
     training
    1.00
     Training
    0.90
     train
    0.88
     batch
    0.87
    Training
    0.87
     samples
    0.84
    train
    0.81
     batches
    0.81
     data
    0.81
    batch
    0.81
    Activations Density 0.471%

    No Known Activations