© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 13926
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the substring "ll"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moser
    -0.68
    bootstrapcdn
    -0.66
     Vieux
    -0.65
    ništ
    -0.64
     Matos
    -0.63
    Simpson
    -0.63
     Koper
    -0.62
    下载附件
    -0.62
     tarta
    -0.61
    EndGlobalSection
    -0.61
    POSITIVE LOGITS
    ll
    2.25
    LL
    2.06
    lls
    1.86
     ll
    1.74
     LL
    1.68
    lll
    1.65
    ell
    1.50
    lla
    1.46
    LLS
    1.45
    llll
    1.39
    Activations Density 0.175%

    No Known Activations