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

    Neuronpedia

    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. 13864
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "write" and its variations in the context of written content

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

    act of writing

    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
     GBIF
    -0.60
    parsedMessage
    -0.58
    anera
    -0.57
    anema
    -0.57
     Cougars
    -0.55
     Alameda
    -0.55
     Trop
    -0.55
     Roskov
    -0.55
     Olympedia
    -0.55
    CppMethod
    -0.55
    POSITIVE LOGITS
     write
    1.18
    write
    1.17
     writing
    1.07
    Write
    1.07
     Write
    1.03
     written
    1.01
     wrote
    0.93
     écrit
    0.93
     Writing
    0.93
    Writing
    0.92
    Activations Density 0.053%

    No Known Activations