© 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-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7378
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and settings in Argentina

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     retos
    -0.58
     acabados
    -0.49
     escoger
    -0.49
     añade
    -0.46
    mainen
    -0.46
    autaire
    -0.45
     alcalde
    -0.44
     gezet
    -0.44
     Ayuntamiento
    -0.44
     coger
    -0.43
    POSITIVE LOGITS
     Argentine
    1.01
     Argentina
    0.94
     Buenos
    0.89
     Argent
    0.89
    Argentina
    0.86
    Argentine
    0.83
     argentino
    0.74
     argentina
    0.73
     Argentino
    0.70
     argent
    0.69
    Activations Density 0.142%

    No Known Activations