© 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. 31-GEMMASCOPE-RES-16K
    11. 2976
    Prev
    Next
    INDEX
    Explanations

    structural and organizational qualities of environments or settings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    descriptions of enclosed spaces and spatial layouts within buildings or rooms.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    OGND
    -0.63
    ñata
    -0.52
    canestro
    -0.50
     EconPapers
    -0.49
    ictwo
    -0.47
    примеча
    -0.44
     fences
    -0.44
    tagext
    -0.44
    arangay
    -0.43
    pédie
    -0.43
    POSITIVE LOGITS
     room
    1.85
     rooms
    1.65
     Room
    1.40
    room
    1.39
     ROOM
    1.33
    Room
    1.28
     Rooms
    1.28
     ROOMS
    1.18
    rooms
    1.16
     ruangan
    1.16
    Activations Density 0.363%

    No Known Activations