© 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. 15-GEMMASCOPE-RES-16K
    11. 4859
    Prev
    Next
    INDEX
    Explanations

    references to evaluation and effectiveness of interventions, particularly in healthcare contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    float
    -0.27
     suced
    -0.27
    MathML
    -0.27
     float
    -0.25
     cada
    -0.23
     Heer
    -0.23
     (
    -0.23
     floats
    -0.23
    ,
    -0.23
     diễn
    -0.22
    POSITIVE LOGITS
    RenderAtEndOf
    0.84
     kasarigan
    0.74
     ब्रेकडाउन
    0.72
    transQ
    0.64
    ₶
    0.64
     Digit
    0.63
    SharedCtor
    0.62
    uillez
    0.62
    TestingModule
    0.61
    ſchaft
    0.61
    Activations Density 2.241%

    No Known Activations