© 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. 28-GEMMASCOPE-RES-16K
    11. 2523
    Prev
    Next
    INDEX
    Explanations

    instances of the word "know" and its various contexts

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

    Follows "know" or identifies hydrodynamics

    np_acts-logits-general · gemini-2.0-flash

    know this, know that

    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
    fuhr
    -0.33
     уве
    -0.30
    RRect
    -0.29
     Dabei
    -0.28
    stopPropagation
    -0.28
     cesse
    -0.28
     Supp
    -0.27
     totul
    -0.27
    ligheter
    -0.26
     جر
    -0.26
    POSITIVE LOGITS
    ロウィン
    0.63
    出版年
    0.62
    queryInterface
    0.61
    Bibliograf
    0.60
     AppModule
    0.60
    Vidite
    0.59
     BMD
    0.57
     المعيارى
    0.57
    ðsíða
    0.57
    <unused98>
    0.57
    Activations Density 0.121%

    No Known Activations