© 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. 31-GEMMASCOPE-RES-16K
    11. 2915
    Prev
    Next
    INDEX
    Explanations

    terms that indicate temporal sequence or transitions in events

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

    the word "Before" at the beginning of sentences or clauses.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     dụ
    -0.36
    DUC
    -0.31
     houden
    -0.30
     voeren
    -0.29
    mitos
    -0.29
    laag
    -0.29
     profonda
    -0.29
    shtml
    -0.28
    eaked
    -0.28
    ㅜ
    -0.28
    POSITIVE LOGITS
    hand
    0.83
    before
    0.74
     Before
    0.71
    andafter
    0.70
    Before
    0.69
    BEFORE
    0.69
     before
    0.67
     BEFORE
    0.66
    HAND
    0.64
     Мексичка
    0.64
    Activations Density 0.118%

    No Known Activations