© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4701
    Prev
    Next
    INDEX
    Explanations

    references to streets and street-related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    errHandler
    -0.80
    Pyx
    -0.76
    oriasis
    -0.72
     accompan
    -0.71
    ukone
    -0.71
    egrave
    -0.68
     للاسماء
    -0.67
     Turch
    -0.67
    msgTypes
    -0.66
     Hemsworth
    -0.65
    POSITIVE LOGITS
     street
    3.36
    street
    2.90
     streets
    2.83
     Street
    2.75
    Street
    2.73
     STREET
    2.67
     Streets
    2.56
    STREET
    2.49
    streets
    2.43
    Streets
    2.34
    Activations Density 0.069%

    No Known Activations