© 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. 2-GEMMASCOPE-RES-16K
    11. 14546
    Prev
    Next
    INDEX
    Explanations

    references to toilets and related bodily functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddHtmlAttribute
    -0.76
     joaat
    -0.60
    TagMode
    -0.54
    はじめに
    -0.51
     auction
    -0.51
    Clifford
    -0.49
     Clifford
    -0.48
     Anniversary
    -0.47
    gó
    -0.47
     Auction
    -0.47
    POSITIVE LOGITS
     feces
    0.96
     urine
    0.86
     vomit
    0.84
     vomiting
    0.81
     excre
    0.76
     Vomiting
    0.71
     vom
    0.70
     Urine
    0.70
     sewage
    0.69
     poop
    0.68
    Activations Density 0.267%

    No Known Activations