© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101828
    Prev
    Next
    INDEX
    Explanations

    references to Kanye West's role as a producer and his contributions to music

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     văn
    -0.47
     tenn
    -0.40
    bsd
    -0.38
     metav
    -0.37
    readyState
    -0.37
     Tail
    -0.35
    RTLE
    -0.35
    ODB
    -0.35
     voks
    -0.35
     voluntary
    -0.34
    POSITIVE LOGITS
     estekak
    0.60
     ThemeData
    0.59
     שוליים
    0.59
    SharedCtor
    0.59
    PreInfinity
    0.57
    WithIOException
    0.56
     المعيارى
    0.53
     InputDecoration
    0.50
     suena
    0.50
    adaptiveStyles
    0.50
    Activations Density 0.012%

    No Known Activations