© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11105
    Prev
    Next
    INDEX
    Explanations

    terms related to specialized fields and roles within various contexts

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

    nouns that denote occupational roles, professional titles, or types of people involved in specific work or activities.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Wikimedijinoj
    -0.56
     feroit
    -0.52
    Напомним
    -0.50
    findpost
    -0.49
    ArrowToggle
    -0.48
    ArgumentParser
    -0.47
    tares
    -0.47
     zwią
    -0.46
    lblNewLabel
    -0.46
     peringatan
    -0.46
    POSITIVE LOGITS
     specialists
    0.61
     dwellers
    0.60
     provider
    0.60
     enthusiasts
    0.59
     providers
    0.57
     guy
    0.57
     afic
    0.57
     leader
    0.55
     holder
    0.54
     wearer
    0.54
    Activations Density 0.690%

    No Known Activations