© 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. 16-GEMMASCOPE-RES-16K
    11. 9475
    Prev
    Next
    INDEX
    Explanations

    references to previous or existing entities and changes in status

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    parsedMessage
    -0.66
    RTEX
    -0.62
     disambiguazione
    -0.61
     autorytatywna
    -0.59
    msgTypes
    -0.58
     فريبيس
    -0.56
     propOrder
    -0.56
    setVerticalGroup
    -0.56
    ValueStyle
    -0.55
    RegressionTest
    -0.55
    POSITIVE LOGITS
    旧
    0.44
     旧
    0.43
     vechi
    0.42
    Old
    0.42
     Former
    0.42
     antiga
    0.41
     retiring
    0.41
     Old
    0.41
     régi
    0.41
     OLD
    0.40
    Activations Density 0.471%

    No Known Activations