© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11644
    Prev
    Next
    INDEX
    Explanations

    numerical data and quantities

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

    Numbers between 0 and 9, and related counting

    np_acts-logits-general · gemini-2.0-flash

    numbers quantifying items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.79
     endblock
    -0.70
    SharedDtor
    -0.69
    complexContent
    -0.65
     ***!
    -0.63
     AssemblyCulture
    -0.62
    makeConstraints
    -0.61
    
    -0.61
    RTDA
    -0.61
    uxxxx
    -0.60
    POSITIVE LOGITS
     six
    0.71
     eight
    0.68
     seven
    0.66
     nine
    0.66
     five
    0.58
     ſeveral
    0.56
     four
    0.56
    Six
    0.55
     Six
    0.54
     additional
    0.53
    Activations Density 1.149%

    No Known Activations