© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 72983
    Prev
    Next
    INDEX
    Explanations

    mentions and references related to DJs and their roles in music

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

    DJ titles and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ParallelGroup
    -0.42
    Pike
    -0.39
     gebildet
    -0.39
     yarar
    -0.39
     mål
    -0.38
     arşivlendi
    -0.38
     urma
    -0.38
    原始内容存档于
    -0.38
     NIS
    -0.38
    RequiresApi
    -0.37
    POSITIVE LOGITS
     DJs
    1.05
     DJ
    1.05
    DJ
    0.95
     dj
    0.91
     Dj
    0.85
    Dj
    0.82
    dj
    0.79
    Discography
    0.67
     Monfieur
    0.66
     ſch
    0.65
    Activations Density 0.005%

    No Known Activations