© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 509
    Prev
    Next
    INDEX
    Explanations

    terms related to bubbles and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "bubble" or "bubbles"

    np_acts-logits-general · gemini-2.0-flash

    air bubbles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.57
     informée
    -0.51
    setVerticalGroup
    -0.49
     GenerationType
    -0.49
    medriver
    -0.47
    ngrx
    -0.46
    MigrationBuilder
    -0.44
    étoit
    -0.42
     виправивши
    -0.42
     InputDecoration
    -0.40
    POSITIVE LOGITS
     bubbles
    1.54
     bubble
    1.50
     Bubble
    1.39
    bubble
    1.35
     Bubbles
    1.30
    Bubble
    1.30
    bubbles
    1.28
    Bubbles
    1.14
     BUB
    1.11
     bubbling
    1.02
    Activations Density 0.376%

    No Known Activations