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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3965
    Prev
    Next
    INDEX
    Explanations

    locations and names associated with Rhode Island

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Rhode Island locations and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    Rhode Island and Providence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.71
     Khrushchev
    -0.70
     doInBackground
    -0.70
     FetchType
    -0.69
     Kyrgyz
    -0.66
     Burkina
    -0.65
     SqlCommand
    -0.64
     Macedonian
    -0.64
     Minangkabau
    -0.63
    enderror
    -0.62
    POSITIVE LOGITS
     Rhode
    1.11
     Providence
    1.06
    Rhode
    0.98
     RI
    0.94
    Providence
    0.92
     URI
    0.80
     Cranston
    0.79
    RI
    0.79
     PROVID
    0.78
     Newport
    0.74
    Activations Density 0.121%

    No Known Activations