© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 93626
    Prev
    Next
    INDEX
    Explanations

    discussions around sharing economic resources and social cooperation

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

    code, technical terms, or symbols

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

    the neuron detects sentence-level punctuation and clause boundaries (commas, periods, quotation marks and other discourse-transition tokens).

    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
    :✨
    -0.94
    GEBURTSDATUM
    -0.80
    Aholisi
    -0.65
    Rhestr
    -0.62
    tanleria
    -0.60
    ソッド
    -0.59
    celotti
    -0.56
     mauva
    -0.54
    arschijnlijk
    -0.52
     ISTAT
    -0.52
    POSITIVE LOGITS
    #+#
    0.54
    httphttps
    0.47
    +#+#
    0.43
    tvguidetime
    0.41
     thru
    0.40
    rungsseite
    0.40
     legit
    0.38
    InstrumentedTest
    0.36
    AddTagHelper
    0.36
     graça
    0.36
    Activations Density 1.770%

    No Known Activations