© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 41877
    Prev
    Next
    INDEX
    Explanations

    references to various types of aircraft

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

    aircraft

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Wend
    -0.47
    InSection
    -0.47
    moreland
    -0.46
    enheim
    -0.46
    pos
    -0.45
    deutig
    -0.43
    Pos
    -0.43
     colpa
    -0.43
     Coz
    -0.42
     row
    -0.41
    POSITIVE LOGITS
     aircraft
    1.66
     Aircraft
    1.65
    Aircraft
    1.62
     AIRCRAFT
    1.45
    aircraft
    1.34
    ircraft
    1.11
     aeron
    1.04
     airc
    1.02
     Flugzeug
    0.96
    飞机
    0.81
    Activations Density 0.008%

    No Known Activations