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

    Neuronpedia

    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. 9-GEMMASCOPE-RES-131K
    11. 66743
    Prev
    Next
    INDEX
    Explanations

    references to nutritional status and related concepts

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

    nutritional and gravitational concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ckså
    -0.68
    retudo
    -0.66
     mosque
    -0.59
     Bewußt
    -0.55
     Geschäft
    -0.54
     lobby
    -0.53
     varandra
    -0.53
     mosques
    -0.52
    ToProps
    -0.52
     Perez
    -0.52
    POSITIVE LOGITS
     nutritional
    1.34
     Nutritional
    1.30
    Nutritional
    1.27
     nutricional
    0.64
    neurial
    0.60
    nutri
    0.57
    inspirational
    0.53
    educational
    0.52
    Educational
    0.52
    ITIONAL
    0.51
    Activations Density 0.007%

    No Known Activations