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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 91101
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal and polar scientific concepts or phenomena

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

    polarizing, legalizing, synchronizing

    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
    Хьажоргаш
    -0.75
    LookAnd
    -0.71
    expandindo
    -0.69
    GEBURTSDATUM
    -0.67
    ----</
    -0.64
    MLLoader
    -0.63
    enumi
    -0.62
     kasarigan
    -0.61
     AssemblyCompany
    -0.61
     kaarangay
    -0.61
    POSITIVE LOGITS
    ized
    1.30
    izing
    1.23
    ization
    1.18
    isation
    1.12
    ize
    1.11
    izations
    1.05
    ised
    1.01
    izer
    0.98
    izes
    0.98
    化
    0.94
    Activations Density 0.143%

    No Known Activations