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. 10009
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and communities in urban 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
    apimachinery
    -0.58
    ibatis
    -0.57
    mapreduce
    -0.53
    ќ
    -0.52
    hbase
    -0.49
    ciclop
    -0.48
     francès
    -0.48
    ellón
    -0.46
     işe
    -0.46
    ︶
    -0.46
    POSITIVE LOGITS
     suburb
    0.94
     suburbs
    0.94
     дописавши
    0.93
     towns
    0.92
     outskirts
    0.87
     suburban
    0.81
     region
    0.80
     hometown
    0.79
     neighborhoods
    0.78
     neighborhood
    0.78
    Activations Density 0.201%

    No Known Activations