© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 14343
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Mex" and its variants, indicating a focus on references to Mexico or related topics

    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
    nonatomic
    -0.68
    protoimpl
    -0.65
    rungsseite
    -0.62
    picasso
    -0.60
    ArrowToggle
    -0.58
    Revenir
    -0.58
    rootDir
    -0.57
    principalTable
    -0.56
    brium
    -0.55
     saurait
    -0.52
    POSITIVE LOGITS
    mex
    1.80
     Mex
    1.14
    Mex
    1.12
     ObjectParameter
    1.06
    PutPixel
    1.05
     mex
    1.03
    MEX
    0.86
     MEX
    0.77
     Requiem
    0.74
     Mehta
    0.73
    Activations Density 0.001%

    No Known Activations