© 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. 38-GEMMASCOPE-RES-16K
    11. 12622
    Prev
    Next
    INDEX
    Explanations

    statistical significance in research findings related to medical studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FishBase
    -0.48
    IndentedString
    -0.47
    sidemargin
    -0.46
    EndGlobalSection
    -0.44
    NewReader
    -0.44
    adpleegd
    -0.44
    horabuena
    -0.43
    altra
    -0.42
    newtheorem
    -0.42
    ьаж
    -0.42
    POSITIVE LOGITS
     statistically
    1.50
     significant
    1.49
     significantly
    1.38
     Significant
    1.36
    Significant
    1.30
    significant
    1.30
     signific
    1.29
     Significantly
    1.22
     SIGNIFIC
    1.15
    significantly
    1.14
    Activations Density 2.007%

    No Known Activations