© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 96411
    Prev
    Next
    INDEX
    Explanations

    terms associated with the deletion of items or properties in a coding or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    delete or remove

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nextProps
    -0.57
    NameInMap
    -0.54
     الرياضيه
    -0.51
     gră
    -0.47
    новништво
    -0.47
     bună
    -0.46
    ItemBackground
    -0.45
     transférez
    -0.44
    assertAll
    -0.43
     TestBed
    -0.43
    POSITIVE LOGITS
     remove
    0.97
     delete
    0.97
    delete
    0.96
    HttpDelete
    0.93
     Delete
    0.93
     删除
    0.92
    remove
    0.90
     removing
    0.87
     removes
    0.86
     removed
    0.85
    Activations Density 0.029%

    No Known Activations