© 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. 22328
    Prev
    Next
    INDEX
    Explanations

    instances of the word "briefing" and its variations

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

    briefing and information summaries

    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
    Portail
    -0.43
    pasang
    -0.43
     solitario
    -0.42
     الحره
    -0.39
    一見
    -0.38
     memasang
    -0.38
    StandardCharsets
    -0.38
     Catan
    -0.37
    VYMaps
    -0.37
    Жен
    -0.36
    POSITIVE LOGITS
     briefing
    1.16
     Briefing
    1.15
     briefed
    0.98
    brief
    0.81
     briefs
    0.73
     Briefs
    0.69
     BRIEF
    0.65
     Brief
    0.65
    Brief
    0.64
     informs
    0.64
    Activations Density 0.009%

    No Known Activations