© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 128872
    Prev
    Next
    INDEX
    Explanations

    instances of legal terminology and concepts related to judgment and evidence

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Mao Tse-tung

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

    the neuron detects salient, topic-signaling content words (important nouns, proper names, and strong modifiers) that mark key information.

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     nuanced
    -0.77
     Notably
    -0.77
     onboarding
    -0.65
     microbiome
    -0.64
     transformative
    -0.63
     incentiv
    -0.63
    Alongside
    -0.63
    tdessen
    -0.62
    伱
    -0.61
     Alongside
    -0.61
    POSITIVE LOGITS
     skall
    0.62
     "..\..\..\
    0.59
     typelib
    0.57
     mußten
    0.57
     muß
    0.57
     idéia
    0.56
    photobucket
    0.55
     mempunyai
    0.53
     "..\..\
    0.52
     mußte
    0.52
    Activations Density 6.445%

    No Known Activations