© 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. 35-GEMMASCOPE-RES-16K
    11. 10393
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers related to mathematical or programming concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Flüssigkeit
    -0.44
     Durchmesser
    -0.43
     Regionen
    -0.41
     diámetro
    -0.40
     líqu
    -0.38
     similaire
    -0.38
     Verhält
    -0.38
     diamètre
    -0.38
     gröss
    -0.36
     Hinblick
    -0.35
    POSITIVE LOGITS
     Jacobi
    0.63
     CAS
    0.62
     hermit
    0.61
     ƒ
    0.61
     PHA
    0.60
     PDR
    0.58
     PTE
    0.58
     BPS
    0.58
     REE
    0.58
     NIST
    0.57
    Activations Density 0.203%

    No Known Activations