© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 6328
    Prev
    Next
    INDEX
    Explanations

    elements of musical composition and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.73
     nahilalakip
    -0.69
    RenderAtEndOf
    -0.67
     témoig
    -0.65
    niſſe
    -0.63
     '\\;'
    -0.61
     doInBackground
    -0.61
    TRIBUN
    -0.60
    şört
    -0.60
    RegressionTest
    -0.59
    POSITIVE LOGITS
     instruments
    0.81
     keyboard
    0.68
     keyboards
    0.67
     organ
    0.61
     piano
    0.61
     instrument
    0.60
     flute
    0.59
     accordion
    0.57
     bass
    0.56
     Instruments
    0.56
    Activations Density 0.132%

    No Known Activations