© 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. 36-GEMMASCOPE-RES-16K
    11. 6484
    Prev
    Next
    INDEX
    Explanations

    references to various legal and regulatory matters related to consumer products and public health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Хьажоргаш
    -0.46
     enfans
    -0.44
    人了
    -0.44
     defaultstate
    -0.44
    aClass
    -0.40
    mCamera
    -0.39
     vœux
    -0.39
     HttpNotFound
    -0.39
     serem
    -0.38
     Chriftian
    -0.36
    POSITIVE LOGITS
     inilah
    0.76
     ayrıca
    0.73
     infatti
    0.72
    AddHtmlAttribute
    0.70
     bowiem
    0.69
    AddTagHelper
    0.68
    들은
    0.68
    quartered
    0.65
     itulah
    0.65
     totiž
    0.63
    Activations Density 1.970%

    No Known Activations