© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 9741
    Prev
    Next
    INDEX
    Explanations

    instances of media coverage and reporting on specific events or situations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     ourselves
    -0.59
     veramente
    -0.59
    anything
    -0.58
     mesmas
    -0.56
    Anything
    -0.55
     Himself
    -0.55
    FlatAppearance
    -0.55
    の人は
    -0.54
    osoever
    -0.54
    יסטוריה
    -0.54
    POSITIVE LOGITS
     recent
    1.29
     efforts
    1.13
    efforts
    1.03
    recent
    1.00
     ongoing
    0.95
    ongoing
    0.93
     recente
    0.91
     RECENT
    0.89
     recentes
    0.86
    Recent
    0.86
    Activations Density 0.458%

    No Known Activations