© 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. 2995
    Prev
    Next
    INDEX
    Explanations

    actions related to the deletion of data or objects

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

    the word "delete" and its variations across different programming and technical contexts.

    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
     المعيارى
    -0.45
    الحياه
    -0.44
    httphttps
    -0.44
    eseorang
    -0.42
     kiin
    -0.41
    onViewCreated
    -0.40
    setVerticalGroup
    -0.39
    :✨
    -0.39
    titleMargin
    -0.39
    WebElementEntity
    -0.39
    POSITIVE LOGITS
     delete
    2.38
     deletion
    2.19
     Delete
    2.14
     deleting
    2.14
    delete
    2.06
     deletes
    2.05
     deleted
    2.03
     Deleting
    1.93
    Delete
    1.92
    删除
    1.89
    Activations Density 0.551%

    No Known Activations