© 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. 456
    Prev
    Next
    INDEX
    Explanations

    references to specific medical concepts or terminologies

    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
    tagHelperRunner
    -0.96
    TagMode
    -0.87
    transQ
    -0.86
     autorytatywna
    -0.85
    exitRule
    -0.82
    XmlAccessType
    -0.82
     MainAxisSize
    -0.81
     HttpNotFound
    -0.80
     المعيارى
    -0.80
     nakalista
    -0.79
    POSITIVE LOGITS
    <eos>
    0.30
    <bos>
    0.27
    readFileSync
    0.24
    かわらず
    0.21
    0
    0.20
    CJK
    0.19
    พาะ
    0.19
     aid
    0.18
    iconque
    0.18
    keyCode
    0.17
    Activations Density 2.662%

    No Known Activations