© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 43271
    Prev
    Next
    INDEX
    Explanations

    terms related to viral detection and the isolation of viruses in laboratory settings

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

    cell culture

    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
     flèche
    -0.39
     cheminée
    -0.39
    cookieParser
    -0.35
     humanidade
    -0.35
    ChildIndex
    -0.34
     législation
    -0.33
    nodoc
    -0.32
     borracha
    -0.32
     angekommen
    -0.31
     maquin
    -0.31
    POSITIVE LOGITS
     culture
    1.30
     Cultures
    1.27
     cultures
    1.26
     Culture
    1.25
    Culture
    1.22
     cultured
    1.18
    culture
    1.16
     CULTURE
    1.14
    cultures
    1.10
    CULTURE
    1.06
    Activations Density 0.571%

    No Known Activations