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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12282
    Prev
    Next
    INDEX
    Explanations

    musical terms and references related to specific cultural instruments

    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
     typelib
    -0.52
    strix
    -0.38
     Bangkok
    -0.36
    -------
    -0.36
     Durchsch
    -0.34
    Thailand
    -0.31
     Thai
    -0.31
    featureID
    -0.31
     Thailand
    -0.31
     bangkok
    -0.31
    POSITIVE LOGITS
     Azerbaijan
    1.11
     Baku
    1.01
     Azer
    0.99
     Azerbai
    0.96
    Azerbaijan
    0.94
    Azer
    0.90
    Baku
    0.81
     Азербай
    0.77
    #
    0.76
    azer
    0.73
    Activations Density 0.119%

    No Known Activations