© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10848
    Prev
    Next
    INDEX
    Explanations

    concepts related to laws, regulations, and federal versus state authority

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

    Following "national" or "federal"

    np_acts-logits-general · gemini-2.0-flash

    national and federal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Życiorys
    -0.41
    DebuggerStep
    -0.38
     privées
    -0.38
    retudo
    -0.38
     HasFactory
    -0.35
     dramatique
    -0.34
     prácti
    -0.34
    testify
    -0.34
    IActionResult
    -0.33
     pě
    -0.33
    POSITIVE LOGITS
     national
    1.73
     nationally
    1.67
     nationwide
    1.64
     global
    1.55
     federal
    1.51
    全国
    1.45
    national
    1.42
     international
    1.41
     globally
    1.41
    global
    1.39
    Activations Density 0.733%

    No Known Activations