© 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. 14-GEMMASCOPE-RES-16K
    11. 5270
    Prev
    Next
    INDEX
    Explanations

    mentions and attributes related to users in a system

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     McIntosh
    -0.45
     McCall
    -0.45
     might
    -0.43
     McNally
    -0.41
     Giordano
    -0.41
    arrête
    -0.40
     McN
    -0.40
     Absch
    -0.40
    สำคัญ
    -0.39
     Espinosa
    -0.39
    POSITIVE LOGITS
     User
    1.30
     user
    1.26
     USER
    1.20
    user
    1.19
     Users
    1.13
     getUser
    1.13
    USER
    1.09
     GetUser
    1.08
    getUser
    1.07
     UserController
    1.05
    Activations Density 0.051%

    No Known Activations