© 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. 6-GEMMASCOPE-RES-16K
    11. 4009
    Prev
    Next
    INDEX
    Explanations

    terms related to bureaucratic processes and governmental actions

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

    administrative or legal processes, especially related to government actions, recalls, or formal procedures.

    oai_token-act-pair · claude-3-5-haiku-20241022
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Datuak
    -0.68
     كومونز
    -0.65
    存于互联网档案馆
    -0.63
     للمعارف
    -0.60
    findpost
    -0.59
     pinulongan
    -0.57
    __);
    -0.56
    ;->
    -0.55
     vVar
    -0.55
    saraba
    -0.55
    POSITIVE LOGITS
    <bos>
    0.56
     JpaRepository
    0.56
     متعلقه
    0.55
     Meksiku
    0.51
    ecutive
    0.51
    AntiForgeryToken
    0.50
     distributed
    0.49
    Rhestr
    0.49
     دیکھیے
    0.49
    SEVER
    0.48
    Activations Density 0.603%

    No Known Activations