© 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-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 3249
    Prev
    Next
    INDEX
    Explanations

    words indicating transformation or change

    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
     pylint
    -0.63
     ſche
    -0.61
     Surveys
    -0.57
    cookieParser
    -0.57
     conftest
    -0.56
    ußt
    -0.55
    ArgumentParser
    -0.54
    nodoc
    -0.54
     houſe
    -0.52
    homonymie
    -0.51
    POSITIVE LOGITS
    become
    0.97
     become
    0.93
    Become
    0.88
     Become
    0.88
    becomes
    0.83
     becomes
    0.82
     BECOME
    0.80
     becoming
    0.79
    became
    0.79
     became
    0.78
    Activations Density 0.071%

    No Known Activations