© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106838
    Prev
    Next
    INDEX
    Explanations

    terms related to political discourse and critiques of governmental authority

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

    non- intra-

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

    the neuron detects politically or morally charged evaluative language—tokens that signal discussion of politics, institutions, social judgments, or strong normative stances.

    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
     nahilalakip
    -0.57
     kasarigan
    -0.55
     Paglinawan
    -0.52
     مواليد
    -0.52
    writeFieldEnd
    -0.51
     GenerationType
    -0.48
    principalColumn
    -0.47
    úgó
    -0.46
    новништво
    -0.46
    Халык
    -0.45
    POSITIVE LOGITS
     Sho
    0.39
    xnn
    0.36
     Tats
    0.36
     <<<<<<<<<<<<<<
    0.35
     المد
    0.35
     счита
    0.35
     Harn
    0.34
     Bres
    0.34
     targeted
    0.34
    mi
    0.34
    Activations Density 0.224%

    No Known Activations