© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1500
    Prev
    Next
    INDEX
    Explanations

    phrases related to opportunities or chances for action

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

    phrases indicating opportunities or chances

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

    opportunity to act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OFDb
    -0.77
     springfox
    -0.70
    出版年
    -0.69
     EconPapers
    -0.66
    kloped
    -0.62
     ervan
    -0.61
    awaiter
    -0.60
    OGND
    -0.59
    ksikon
    -0.59
    kington
    -0.58
    POSITIVE LOGITS
     démocr
    0.52
     Répondre
    0.52
    地说道
    0.50
     choose
    0.50
     firsthand
    0.46
    oggi
    0.46
     audition
    0.46
     experience
    0.46
     decide
    0.46
     conhe
    0.45
    Activations Density 0.040%

    No Known Activations