© 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. 3-GEMMASCOPE-RES-16K
    11. 4387
    Prev
    Next
    INDEX
    Explanations

    verbs associated with past actions and accomplishments

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     doInBackground
    -0.74
     Roskov
    -0.72
    PhysRevD
    -0.72
    évaluateur
    -0.71
     ChromeDriver
    -0.70
    GHIJKLM
    -0.69
    __":
    -0.69
    참고
    -0.66
    uxxxx
    -0.66
    حوالہ
    -0.66
    POSITIVE LOGITS
     been
    0.70
     recent
    0.67
     geweest
    0.65
    been
    0.62
     recentemente
    0.61
     vært
    0.59
     récemment
    0.58
     recientemente
    0.58
     blitt
    0.57
     recently
    0.57
    Activations Density 0.328%

    No Known Activations