© 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. 10348
    Prev
    Next
    INDEX
    Explanations

    technical terms related to geographical and elevation mapping

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     nakalista
    -0.60
    yntaxException
    -0.57
    lccn
    -0.57
    WebElementEntity
    -0.52
    didSet
    -0.47
    parsedMessage
    -0.46
     unknownFields
    -0.46
    ScopeManager
    -0.45
     Administrativna
    -0.45
    
    -0.45
    POSITIVE LOGITS
     aufge
    0.45
    lapsingToolbar
    0.40
     via
    0.36
    RunAsync
    0.34
    iring
    0.34
     получится
    0.33
     Comp
    0.33
    esterno
    0.33
     получается
    0.33
     Kooper
    0.32
    Activations Density 1.914%

    No Known Activations