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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 4537
    Prev
    Next
    INDEX
    Explanations

    specific geographical and contextual references related to South America, particularly Chile, Peru, and the Andean region

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Garza
    -0.59
     Galveston
    -0.57
     rubles
    -0.56
     Ekiti
    -0.56
     يتيمه
    -0.53
     cubanos
    -0.52
    ázquez
    -0.51
    ilions
    -0.50
     Nigerian
    -0.50
     Attila
    -0.49
    POSITIVE LOGITS
     Peru
    1.07
     Peruvian
    1.02
     Cusco
    0.96
    Peru
    0.95
     Lima
    0.91
     Perú
    0.91
     peruan
    0.86
     Tahu
    0.85
    Lima
    0.80
     Inca
    0.80
    Activations Density 0.125%

    No Known Activations