© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 8204
    Prev
    Next
    INDEX
    Explanations

    instances of the word "one" and related contextual phrases involving singular items or actions

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

    following "one" or "SNP"

    np_acts-logits-general · gemini-2.0-flash

    one of a kind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alguma
    -0.40
     first
    -0.40
     eerste
    -0.35
     nogen
    -0.34
     اولین
    -0.33
     erste
    -0.33
     algum
    -0.32
     primeira
    -0.32
     première
    -0.31
     primeiras
    -0.31
    POSITIVE LOGITS
    tagHelperRunner
    0.90
     فريبيس
    0.82
     apiece
    0.78
     estekak
    0.73
    ValueStyle
    0.71
    씩
    0.69
     per
    0.67
     للاسماء
    0.66
    bootstrapcdn
    0.65
     åt
    0.63
    Activations Density 0.340%

    No Known Activations