© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 9484
    Prev
    Next
    INDEX
    Explanations

    the word "para" and its variations in the context of instructions or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jména
    -1.00
     Orrell
    -0.86
     couverts
    -0.83
     économies
    -0.78
     banques
    -0.76
     fermés
    -0.75
     acoper
    -0.75
    ation
    -0.74
     sánchez
    -0.73
     aveug
    -0.73
    POSITIVE LOGITS
     para
    1.69
    Para
    1.44
     PARA
    1.41
     Para
    1.41
    para
    1.26
    PARA
    1.19
     untuk
    1.14
     pour
    1.14
     для
    1.07
    Untuk
    1.07
    Activations Density 0.234%

    No Known Activations