© 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. 31-GEMMASCOPE-RES-16K
    11. 2999
    Prev
    Next
    INDEX
    Explanations

    references to design concepts and terminology

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    the word "Design" appearing as a standalone term or label in text.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     nakalista
    -0.70
    kpop
    -0.42
     ארו
    -0.40
     AssemblyVersion
    -0.40
    Източници
    -0.39
    alnız
    -0.39
     obro
    -0.39
     administração
    -0.39
    utenants
    -0.38
    reportWebVitals
    -0.38
    POSITIVE LOGITS
     Design
    0.65
    Design
    0.62
    TypedDataSet
    0.61
    StructEnd
    0.60
     Designers
    0.54
     Designer
    0.53
    Designer
    0.52
     designer
    0.51
     DESIGN
    0.50
     Redesign
    0.50
    Activations Density 0.153%

    No Known Activations