© 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. 86209
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate dismissive attitudes or arguments about serious issues

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

    found that

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects discussion of court rulings, legal findings, and judgments about appeals or trial errors.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     '\\;'
    -0.73
    ंदीखरीदारी
    -0.60
     tartalomajánló
    -0.54
     esternos
    -0.53
     يتيمه
    -0.52
     chi̍t
    -0.52
    routeProvider
    -0.52
    rrggbb
    -0.50
     CreateTagHelper
    -0.50
     noDo
    -0.50
    POSITIVE LOGITS
    انيف
    0.35
     flats
    0.34
     сталь
    0.33
    scaron
    0.33
    動画
    0.33
    nalpot
    0.32
    bcc
    0.32
     tecnici
    0.32
     kons
    0.31
    化
    0.31
    Activations Density 0.103%

    No Known Activations