© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6691
    Prev
    Next
    INDEX
    Explanations

    elements related to music genre descriptions, particularly house and dance music

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.45
     كومونز
    -0.40
    GeneratedMessage
    -0.40
    TabItem
    -0.40
    GetKeyDown
    -0.40
    jfree
    -0.39
    queryInterface
    -0.39
     ак
    -0.38
     Snowy
    -0.38
     trem
    -0.38
    POSITIVE LOGITS
     DJ
    0.60
     dj
    0.54
    DJ
    0.54
     DJs
    0.49
     Ibiza
    0.48
     Dj
    0.47
    ьаж
    0.44
    Dj
    0.44
    soundcloud
    0.43
    dj
    0.43
    Activations Density 0.122%

    No Known Activations