© 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 EvalsExportsinterp-engineNEWAPI 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. 116269
    Prev
    Next
    INDEX
    Explanations

    connections between cause and effect

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

    time or comparison prepositions

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

    the neuron detects discourse or stance markers — short words that signal emphasis, evaluation, comparison, or framing (e.g., "truth", "clear", "more/than", "for", "into", "able").

    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
     Comprometido
    -0.30
    ientôt
    -0.28
     Aérea
    -0.28
    seits
    -0.27
     Außerdem
    -0.27
     Савезне
    -0.25
     Dänemark
    -0.25
     Sementara
    -0.25
     sebelah
    -0.25
    })));
    -0.25
    POSITIVE LOGITS
    <unused79>
    0.85
    <unused52>
    0.85
    <unused74>
    0.85
    <unused43>
    0.85
    <unused47>
    0.85
    <unused23>
    0.85
    <unused41>
    0.85
    <unused16>
    0.85
    [@BOS@]
    0.85
    <unused8>
    0.85
    Activations Density 0.291%

    No Known Activations