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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1231
    Prev
    Next
    INDEX
    Explanations

    street names and addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.46
    </em>
    -0.43
     AssemblyCulture
    -0.43
    "]();
    -0.43
     åt
    -0.42
    　　【
    -0.42
    ")).
    -0.41
     papiers
    -0.41
    >();
    -0.41
     menny
    -0.41
    POSITIVE LOGITS
     Avenue
    1.11
     Street
    0.99
     Road
    0.97
     Ave
    0.95
     Boulevard
    0.95
    Avenue
    0.95
     Blvd
    0.94
     AVENUE
    0.92
     Rd
    0.91
    IndentedString
    0.90
    Activations Density 0.181%

    No Known Activations