© 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. 31-GEMMASCOPE-RES-16K
    11. 4289
    Prev
    Next
    INDEX
    Explanations

    references to natural compounds and their health benefits

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

    scientific and medical terminology related to health, disease, and biological research.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.63
     MainAxisSize
    -0.57
     noDo
    -0.57
    :✨
    -0.56
    delwed
    -0.52
     MUCH
    -0.51
    点此举报
    -0.50
    存于互联网档案馆
    -0.49
    /**
    -0.49
     يتيمه
    -0.47
    POSITIVE LOGITS
    Nowadays
    0.84
     Nowadays
    0.79
     Moreover
    0.65
    Moreover
    0.61
    mainly
    0.60
     nowadays
    0.60
     mainly
    0.59
    Concerning
    0.58
     Nevertheless
    0.57
     firstly
    0.55
    Activations Density 7.533%

    No Known Activations