Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1068
    Prev
    Next
    INDEX
    Explanations

    terms related to drive-thrus and drive units

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

    references to transportation or delivery methods

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

    drive

    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
    XmlAccessType
    -0.74
    tvguidetime
    -0.69
     continúas
    -0.63
     considérons
    -0.63
    CrossRef
    -0.62
    ViewImports
    -0.61
     gynhyrchwyd
    -0.60
     onCancelled
    -0.59
    spesies
    -0.59
    RectangleBorder
    -0.59
    POSITIVE LOGITS
     drive
    0.66
    drive
    0.59
     Drive
    0.59
     للمعارف
    0.54
    Drive
    0.53
     dri
    0.52
     drives
    0.52
     nahilalakip
    0.51
     DRIVE
    0.50
     train
    0.49
    Activations Density 0.017%

    No Known Activations