© 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. 81462
    Prev
    Next
    INDEX
    Explanations

    words related to music, especially brass instruments and military themes

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

    brass band fanfare trumpet bell gun

    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
    жах
    -0.33
     GenerationType
    -0.31
    rungsseite
    -0.31
    Schedulers
    -0.30
     "..\..\
    -0.29
     base
    -0.29
     rom
    -0.29
    企
    -0.29
    Stab
    -0.28
     Roman
    -0.28
    POSITIVE LOGITS
     fanfare
    0.68
     trumpet
    0.60
     kasarigan
    0.58
     trumpets
    0.57
     cannons
    0.57
     artillery
    0.56
    Бахар
    0.55
    CppMethod
    0.54
     gynhyrchwyd
    0.54
     Fireworks
    0.54
    Activations Density 0.023%

    No Known Activations