© 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. 0-GEMMASCOPE-RES-16K
    11. 15112
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical data or IDs associated with patents and research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desmotivaciones
    -1.56
     ainfi
    -1.41
     increí
    -1.32
     queſta
    -1.32
     plufieurs
    -1.31
     avoient
    -1.29
     ویکی‌پدی
    -1.27
     feroit
    -1.27
    parsedMessage
    -1.23
    pecabe
    -1.23
    POSITIVE LOGITS
     
    1.51
    _
    1.34
    ↵
    1.32
    /
    1.29
      
    1.25
     (
    1.25
    ,
    1.22
     A
    1.18
     B
    1.17
    c
    1.16
    Activations Density 1.491%

    No Known Activations