© 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. 40-GEMMASCOPE-RES-16K
    11. 4014
    Prev
    Next
    INDEX
    Explanations

    references to music bands and performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    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
    -0.47
     estekak
    -0.42
     pochette
    -0.40
     Vertra
    -0.38
     pajak
    -0.38
     Füße
    -0.38
     detalladas
    -0.38
    tagHelperRunner
    -0.38
    下载附件
    -0.36
    exitRule
    -0.36
    POSITIVE LOGITS
     Blink
    0.63
     Incub
    0.59
     Guns
    0.59
     Maroon
    0.58
     Wee
    0.57
     Coldplay
    0.57
     Nirvana
    0.57
     Param
    0.57
     Muse
    0.56
     Counting
    0.56
    Activations Density 0.217%

    No Known Activations