© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 16220
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing exclusivity or uniqueness

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     initComponents
    -0.50
    Slf
    -0.42
     prit
    -0.38
    makeConstraints
    -0.38
     shaky
    -0.38
     通販
    -0.38
     steady
    -0.36
     hazy
    -0.36
     viewDid
    -0.36
    Tsu
    -0.35
    POSITIVE LOGITS
    不但
    0.66
     nejen
    0.65
    AddTagHelper
    0.63
    Either
    0.62
    either
    0.61
    NameInMap
    0.61
     AssemblyCulture
    0.60
    不仅
    0.60
    不僅
    0.57
     either
    0.56
    Activations Density 0.094%

    No Known Activations