© 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. 10-GEMMASCOPE-RES-16K
    11. 2758
    Prev
    Next
    INDEX
    Explanations

    specific programming structures and syntax elements used in data manipulation and coding

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     estekak
    -0.59
     للمعارف
    -0.59
     oposición
    -0.50
    hoeddwyd
    -0.50
     برانيه
    -0.48
     conhece
    -0.47
     émissions
    -0.47
     Escolar
    -0.46
     насељу
    -0.46
    ourite
    -0.45
    POSITIVE LOGITS
     uParam
    0.46
    RegistryLite
    0.45
    yntaxException
    0.41
    enterOuterAlt
    0.38
    MethodManager
    0.38
     <>",
    0.36
    aspetto
    0.35
    iprot
    0.35
    prepareStatement
    0.34
    NameInMap
    0.34
    Activations Density 0.667%

    No Known Activations