© 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. 34-GEMMASCOPE-RES-16K
    11. 3135
    Prev
    Next
    INDEX
    Explanations

    references to corporate roles and leadership positions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     HasFactory
    -0.36
     secretariat
    -0.34
    coordinator
    -0.34
     coordinators
    -0.34
     []:
    -0.34
    scre
    -0.33
     suelos
    -0.33
    事務
    -0.32
     са
    -0.31
     manteiga
    -0.31
    POSITIVE LOGITS
     vice
    1.09
     VP
    1.04
     Vice
    1.00
     SVP
    0.98
    Vice
    0.94
     Senior
    0.94
     vp
    0.93
    VP
    0.89
    Senior
    0.89
     senior
    0.88
    Activations Density 0.214%

    No Known Activations