© 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. 7179
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "AD" and related terms in medical contexts

    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
    Vidite
    -0.35
    PickerController
    -0.34
     Italijani
    -0.34
     autorytatywna
    -0.34
    MergeFrom
    -0.33
    舺
    -0.32
    oredCriteria
    -0.32
    Hentet
    -0.31
     betweenstory
    -0.31
     otomatig
    -0.31
    POSITIVE LOGITS
     Ad
    1.94
     AD
    1.93
    Ad
    1.89
    AD
    1.86
    ad
    1.85
    ads
    1.76
     ad
    1.73
    adi
    1.64
     Adi
    1.63
     adi
    1.62
    Activations Density 0.418%

    No Known Activations