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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 55521
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "draft" in various contexts

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

    draft document or report

    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
     bedrijven
    -0.56
     mulher
    -0.52
     serviceName
    -0.51
     jongen
    -0.50
     şirket
    -0.49
    companyName
    -0.48
     getItemId
    -0.47
     bedrijf
    -0.47
     useAppContext
    -0.47
    COMPANY
    -0.46
    POSITIVE LOGITS
     draft
    2.61
     Draft
    2.48
    Draft
    2.42
    draft
    2.27
     DRAFT
    2.22
     drafts
    2.06
    DRAFT
    1.94
     drafted
    1.77
     draught
    1.70
     drafting
    1.64
    Activations Density 0.004%

    No Known Activations