© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 1391
    Prev
    Next
    INDEX
    Explanations

    important events or concepts related to elections and advertising

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    individuals who disseminate advertising or suppose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    SharedDtor
    -0.85
     betweenstory
    -0.84
     estekak
    -0.80
     الرياضيه
    -0.73
    цездатний
    -0.72
    httphttps
    -0.70
     ivelany
    -0.70
    Datuak
    -0.70
     يتيمه
    -0.69
    OGND
    -0.68
    POSITIVE LOGITS
    做一个
    0.34
     
    0.33
     recent
    0.32
     used
    0.32
     recently
    0.31
     job
    0.31
     good
    0.28
    족
    0.28
    kmal
    0.28
    ’
    0.28
    Activations Density 0.000%

    No Known Activations