© 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
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 673
    Prev
    Next
    INDEX
    Explanations

    concepts related to economic systems and property ownership

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

    money to maintain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     key
    -0.36
     focused
    -0.32
     уг
    -0.31
     тре
    -0.31
     G
    -0.31
     series
    -0.30
     synthèse
    -0.30
    key
    -0.30
    第一
    -0.29
     Sitz
    -0.29
    POSITIVE LOGITS
     queſta
    0.79
    tagHelperRunner
    0.75
     reinvest
    0.72
    contentLoaded
    0.69
     Wikimedijinoj
    0.67
    FundMe
    0.66
    ArgumentParser
    0.65
    存于互联网档案馆
    0.63
     متعلقه
    0.62
     informée
    0.61
    Activations Density 0.139%

    No Known Activations