© 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. 20722
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "write" and related variants in a technical or programming context

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

    write operations

    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
    CppMethod
    -0.70
     $_(
    -0.69
     SFC
    -0.68
    LookAnd
    -0.68
     categoryId
    -0.67
     companyId
    -0.66
    assertAll
    -0.65
     Roskov
    -0.65
     Mons
    -0.65
    oulos
    -0.65
    POSITIVE LOGITS
    write
    1.23
    Write
    1.16
     Write
    1.09
     write
    1.05
    WRITE
    0.94
     escritura
    0.88
     WRITE
    0.87
     writing
    0.78
     écrire
    0.75
     writes
    0.74
    Activations Density 0.028%

    No Known Activations