© 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. 3016
    Prev
    Next
    INDEX
    Explanations

    questions that start with variations of "are," "am," or "is."

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

    the word "Are" at the beginning of questions or sentences.

    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
    ConstraintMaker
    -0.52
     Lightboxes
    -0.49
    Autoritní
    -0.45
     esternos
    -0.45
     ComVisible
    -0.43
    …~
    -0.42
    styleType
    -0.42
    She
    -0.42
    SequentialGroup
    -0.41
     termica
    -0.41
    POSITIVE LOGITS
     you
    0.77
     we
    0.71
     they
    0.65
     YOU
    0.50
    you
    0.42
     ustedes
    0.41
     jsme
    0.40
     I
    0.39
     они
    0.38
     Nós
    0.37
    Activations Density 0.102%

    No Known Activations