© 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. 21-GEMMASCOPE-RES-16K
    6. 12316
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and their significance in historical or agricultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Méditerranée
    -0.57
     déploy
    -0.57
    ázquez
    -0.53
    Algérie
    -0.53
     Blade
    -0.52
     Garza
    -0.51
     Massen
    -0.50
    LVANIA
    -0.50
     hés
    -0.49
     Geral
    -0.48
    POSITIVE LOGITS
     Peruvian
    1.00
     Peru
    0.97
    Peru
    0.90
     Cusco
    0.88
     alpaca
    0.83
     Inca
    0.82
     Machu
    0.80
    peru
    0.78
     оригіналу
    0.77
     Lima
    0.76
    Activations Density 0.070%

    No Known Activations