© 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. 15-GEMMASCOPE-RES-16K
    11. 9847
    Prev
    Next
    INDEX
    Explanations

    instances of juvenile mischief and rebellion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.63
    ValueStyle
    -0.62
    навли
    -0.49
    MessageOf
    -0.48
     vermitteln
    -0.48
    PLACE
    -0.46
    cog
    -0.45
    posedge
    -0.45
    zepte
    -0.44
    发表于
    -0.44
    POSITIVE LOGITS
     unauthorized
    0.80
     unauthorised
    0.78
     prank
    0.78
     mischief
    0.77
     pranks
    0.75
     naughty
    0.74
     unsupervised
    0.71
     unlawful
    0.70
     illegal
    0.69
     Unauthorized
    0.68
    Activations Density 0.277%

    No Known Activations