© 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. 31-GEMMASCOPE-RES-131K
    11. 89708
    Prev
    Next
    INDEX
    Explanations

    terms associated with governance, social services, and collaborative efforts in various sectors

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

    governance, education, nutrition, industry, laws, exchanges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.59
     iNdEx
    -0.57
    ResumeLayout
    -0.52
     oddly
    -0.49
    bitField
    -0.47
    writeFieldEnd
    -0.47
     câte
    -0.47
    sometimes
    -0.47
     sometimes
    -0.46
     مشين
    -0.46
    POSITIVE LOGITS
     particularly
    0.71
    particularly
    0.64
     especially
    0.64
     Particularly
    0.63
     Especially
    0.59
     khususnya
    0.59
    Improving
    0.58
    引き続き
    0.57
    特别是
    0.57
     strengthen
    0.57
    Activations Density 0.031%

    No Known Activations