© 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. 9-GEMMASCOPE-RES-131K
    11. 82804
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical definitions and concepts

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

    specifying degree or extent

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

    The neuron detects words that express emphasis, importance, or degree — i.e., intensifiers and strong evaluative terms.

    oai_token-act-pair · gpt-5-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.69
     Nowadays
    -0.59
    Nowadays
    -0.55
     nowadays
    -0.54
    Moreover
    -0.52
     shrimps
    -0.51
     freezed
    -0.48
     equipments
    -0.48
     Moreover
    -0.47
     respectivas
    -0.47
    POSITIVE LOGITS
     preventative
    0.69
    Datuak
    0.67
     gleaned
    0.63
    agerie
    0.63
    spanning
    0.62
     interpretive
    0.61
    )_/¯
    0.61
     leapt
    0.60
    checkFor
    0.60
    principalColumn
    0.59
    Activations Density 13.001%

    No Known Activations