© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 457
    Prev
    Next
    INDEX
    Explanations

    references to national topics, issues, or organizations

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

    "national"

    np_acts-logits-general · gemini-2.0-flash

    national

    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
    elry
    -0.45
    elbow
    -0.43
    ChildScrollView
    -0.41
    closet
    -0.39
    enumi
    -0.39
     MoU
    -0.39
     curé
    -0.37
    PerformLayout
    -0.37
     drizzle
    -0.36
     noDo
    -0.36
    POSITIVE LOGITS
     national
    1.15
     National
    1.12
    National
    1.05
     NATIONAL
    0.93
    national
    0.92
    NATIONAL
    0.88
     Nationwide
    0.88
     Nacional
    0.82
     Nation
    0.82
    Nacional
    0.82
    Activations Density 0.080%

    No Known Activations