© 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. 30-GEMMASCOPE-RES-16K
    11. 11881
    Prev
    Next
    INDEX
    Explanations

    numerical and statistical data related to medical or scientific research outcomes

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

    preceding "respectively"

    np_acts-logits-general · gemini-2.0-flash

    lists ending with respectively

    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
    fitrión
    -0.54
    省市镇
    -0.48
    Somehow
    -0.47
     ویکی‌پدی
    -0.46
     ligiloj
    -0.44
    SharedDtor
    -0.42
     AssemblyCulture
    -0.42
    setupUi
    -0.41
     Somehow
    -0.41
     informée
    -0.41
    POSITIVE LOGITS
     respectively
    3.47
    respectively
    2.95
     respectivamente
    2.88
     respectivement
    2.47
     соответственно
    2.14
     respective
    2.13
     rispet
    1.90
     respec
    1.81
    respective
    1.80
    分别
    1.60
    Activations Density 0.828%

    No Known Activations