© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 110684
    Prev
    Next
    INDEX
    Explanations

    comments or documentation within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fusca
    -0.33
     transmission
    -0.33
    RetentionPolicy
    -0.31
     ainsi
    -0.31
    GGG
    -0.31
     deposition
    -0.30
     skj
    -0.29
     والن
    -0.29
    ServletContext
    -0.29
     totalPrice
    -0.29
    POSITIVE LOGITS
     nonUne
    0.76
     betweenstory
    0.64
    IsContent
    0.57
    AnchorStyles
    0.52
    MemoryWarning
    0.51
    aronder
    0.50
     Penyakit
    0.49
    ⩕
    0.49
     verſch
    0.48
     insuffisamment
    0.48
    Activations Density 0.009%

    No Known Activations