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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 14999
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate expectations or requirements pertaining to agreements and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TintMode
    -0.66
    webElementXpaths
    -0.64
    ⓧ
    -0.63
     jScrollPane
    -0.58
    CppCodeGen
    -0.55
     utk
    -0.54
    jsdelivr
    -0.53
     सत्यापित
    -0.51
     manuscrit
    -0.51
     通販
    -0.51
    POSITIVE LOGITS
     quelconque
    0.70
     aquilo
    0.67
     oftentimes
    0.65
     things
    0.61
     Anybody
    0.60
     magari
    0.59
     whatnot
    0.58
     Verg
    0.57
    featureID
    0.57
     useParams
    0.56
    Activations Density 0.224%

    No Known Activations