© 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. 30-GEMMASCOPE-RES-16K
    11. 12481
    Prev
    Next
    INDEX
    Explanations

    closing parentheses within code and mathematical expressions

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

    LaTeX syntax for array or matrix environments

    np_acts-logits-general · gemini-2.0-flash

    beginnings of structured content

    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
     betweenstory
    -0.49
    lgari
    -0.47
    WD
    -0.44
     Signalez
    -0.41
     propOrder
    -0.39
     الحره
    -0.38
     ovens
    -0.38
    人民
    -0.38
     jspb
    -0.38
    wd
    -0.37
    POSITIVE LOGITS
     begin
    0.73
    begin
    0.63
     beginning
    0.62
     begins
    0.61
     börjar
    0.57
    <table>
    0.56
     begun
    0.55
     înce
    0.55
     Beginning
    0.55
     BEGINNING
    0.54
    Activations Density 0.409%

    No Known Activations