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. 12-GEMMASCOPE-RES-16K
    6. 4336
    Prev
    Next
    INDEX
    Explanations

    references to villages or communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sardegna
    -0.60
    modb
    -0.52
    ISSIPPI
    -0.49
    CONSIN
    -0.49
     विश्वसनीयता
    -0.48
     Kauai
    -0.48
    AYSIA
    -0.47
    edig
    -0.45
     anyone
    -0.45
     işe
    -0.45
    POSITIVE LOGITS
     town
    1.00
     towns
    0.97
     cities
    0.85
     city
    0.83
     AppCompat
    0.82
     getCity
    0.81
    thâu
    0.80
     municipality
    0.79
    SceneManagement
    0.78
     villages
    0.77
    Activations Density 0.277%

    No Known Activations