© 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. 20-GEMMASCOPE-RES-131K
    11. 36389
    Prev
    Next
    INDEX
    Explanations

    occurrences of subtraction-related terms and operations

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

    subtract and subtraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.63
     препратки
    -0.63
    __*/
    -0.61
    httphttps
    -0.57
     HasFactory
    -0.56
    sizeCache
    -0.56
     ProtoMessage
    -0.54
    msgTypes
    -0.53
    webElementXpaths
    -0.52
     lenker
    -0.50
    POSITIVE LOGITS
     subtraction
    0.88
     subtra
    0.83
     subtract
    0.79
     subtracting
    0.79
    Subtract
    0.69
     Subtraction
    0.68
    subtract
    0.65
     subtracted
    0.65
    HttpDelete
    0.65
     Subtract
    0.58
    Activations Density 0.066%

    No Known Activations