© 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. 15-GEMMASCOPE-RES-16K
    11. 6229
    Prev
    Next
    INDEX
    Explanations

    references to various types of rooms and their characteristics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Heritage
    -0.48
    enlace
    -0.43
     Hackett
    -0.42
     ła
    -0.41
    Heritage
    -0.41
     huelga
    -0.40
    แก่
    -0.40
     strike
    -0.40
    Hãy
    -0.40
     प्राप्त
    -0.40
    POSITIVE LOGITS
     Room
    1.43
    Room
    1.42
     room
    1.40
     ROOM
    1.38
     rooms
    1.31
    room
    1.30
     Rooms
    1.28
    ROOM
    1.27
    rooms
    1.21
    Rooms
    1.18
    Activations Density 0.079%

    No Known Activations