Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 1491
    Prev
    Next
    INDEX
    Explanations

    references to Spain and elements of Spanish culture, including food and historical contexts

    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
     kasarigan
    -0.95
     صوتيه
    -0.85
     الحره
    -0.76
     Asunción
    -0.74
    évaluateur
    -0.73
     Roskov
    -0.71
     pirata
    -0.71
     Ríos
    -0.69
     Venise
    -0.69
     Mexicano
    -0.68
    POSITIVE LOGITS
     Spain
    1.16
     Spanish
    1.08
    Spain
    0.99
    MADRID
    0.97
    Espagne
    0.94
    Spanish
    0.87
     spain
    0.86
     Испании
    0.85
     Madrid
    0.85
     spanish
    0.83
    Activations Density 0.287%

    No Known Activations