© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14349
    Prev
    Next
    INDEX
    Explanations

    instances of the term "write" or variations indicating writing actions

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

    the verb "write"

    np_acts-logits-general · gemini-2.0-flash

    writing actions

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    parsedMessage
    -0.63
    anema
    -0.63
     Roskov
    -0.60
     Cougars
    -0.60
     GBIF
    -0.59
    ellido
    -0.58
     $_(
    -0.58
    Coco
    -0.57
    
    -0.57
    CppMethod
    -0.56
    POSITIVE LOGITS
    write
    1.23
     write
    1.22
    Write
    1.13
     writing
    1.10
     Write
    1.09
     written
    1.02
     wrote
    0.96
     Writing
    0.96
    writing
    0.95
    Writing
    0.95
    Activations Density 0.129%

    No Known Activations