© 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. 23-GEMMASCOPE-RES-16K
    11. 10022
    Prev
    Next
    INDEX
    Explanations

    logging actions and error messages in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.90
    DockStyle
    -0.80
    bootstrapcdn
    -0.79
    Personendaten
    -0.71
     MainAxisSize
    -0.69
    IsContent
    -0.69
    IntoConstraints
    -0.68
    Tembelea
    -0.66
     rhestr
    -0.65
    majánló
    -0.65
    POSITIVE LOGITS
    console
    0.39
    TODO
    0.37
     said
    0.35
     saying
    0.34
     step
    0.34
    print
    0.34
    printf
    0.30
     poitrine
    0.30
     noted
    0.30
    step
    0.29
    Activations Density 0.139%

    No Known Activations