© 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 - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 6105
    Prev
    Next
    INDEX
    Explanations

    phrases related to the effects and consequences of various subjects on different outcomes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
    Negative Logits
     atve
    -0.37
     cewek
    -0.37
     ibunya
    -0.35
     Keuangan
    -0.35
    étoit
    -0.34
     vermelhas
    -0.34
     Schrifts
    -0.33
     näytte
    -0.33
    šanās
    -0.33
     précédentes
    -0.33
    POSITIVE LOGITS
     Impact
    1.20
     IMPACT
    1.18
    Impact
    1.15
     impact
    1.07
    IMPACT
    1.02
    impact
    1.01
     Impacts
    0.94
     impacting
    0.93
    Impacts
    0.92
     impacto
    0.88
    Activations Density 0.076%

    No Known Activations