© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 15625
    Prev
    Next
    INDEX
    Explanations

    references to the word "Mad" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildIndex
    -0.81
     propOrder
    -0.80
    UTERS
    -0.78
    fjspx
    -0.70
    IsContent
    -0.68
    afone
    -0.67
    oneph
    -0.66
    __*/
    -0.66
    chymal
    -0.65
    HtmlAttribute
    -0.62
    POSITIVE LOGITS
     Mad
    1.03
    Mad
    0.95
     mad
    0.90
     MAD
    0.71
    mad
    0.69
    MAD
    0.69
     Madd
    0.58
     Maddox
    0.57
     Madsen
    0.53
    atory
    0.51
    Activations Density 0.057%

    No Known Activations