© 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. 21-GEMMASCOPE-RES-16K
    11. 10610
    Prev
    Next
    INDEX
    Explanations

    code related to database operations and XML writing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.64
     lenker
    -0.64
    tvguidetime
    -0.64
    KURZBESCHREIBUNG
    -0.62
     ujednoznacz
    -0.60
    Tembelea
    -0.60
     للاسماء
    -0.59
     transfieras
    -0.57
     CommonModule
    -0.55
    expandindo
    -0.54
    POSITIVE LOGITS
    prepareStatement
    0.85
     BufferedWriter
    0.50
    BagConstraints
    0.47
    URLConnection
    0.45
    ExecuteReader
    0.43
    DataOutputStream
    0.41
    SupportActionBar
    0.40
     PrintWriter
    0.40
    timmt
    0.39
     Vorbereitung
    0.36
    Activations Density 0.206%

    No Known Activations