© 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. 28-GEMMASCOPE-RES-16K
    11. 3623
    Prev
    Next
    INDEX
    Explanations

    phrases related to cancer research and genetic studies

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

    Numbers modifying a noun

    np_acts-logits-general · gemini-2.0-flash

    numbers found or counted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     سكانية
    -0.47
    хьтан
    -0.45
     kaarangay
    -0.41
    writeFieldEnd
    -0.39
    RuleContext
    -0.38
     oprot
    -0.38
    AutoScaleMode
    -0.38
     Wicidata
    -0.37
    sproz
    -0.35
    HasColumnName
    -0.35
    POSITIVE LOGITS
     nine
    1.70
     eight
    1.66
     seven
    1.66
     six
    1.53
     dozens
    1.52
     eleven
    1.44
     thirteen
    1.42
     dozen
    1.41
     five
    1.37
     fourteen
    1.37
    Activations Density 1.341%

    No Known Activations