© 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. 1-GEMMASCOPE-RES-16K
    6. 7376
    Prev
    Next
    INDEX
    Explanations

    references to locations and historical figures related to Berlin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Witherspoon
    -0.70
     Lucinda
    -0.64
    FieldNumber
    -0.62
     Audiodateien
    -0.60
     acamp
    -0.59
     Jodie
    -0.59
    bitat
    -0.57
     Nant
    -0.57
     tana
    -0.57
     Frist
    -0.57
    POSITIVE LOGITS
     Continental
    0.86
    Continental
    0.82
     Berlin
    0.80
     continental
    0.75
    Julius
    0.73
    Berlin
    0.73
    continent
    0.72
     Ferdinand
    0.71
     Georg
    0.70
     Lutheran
    0.70
    Activations Density 3.030%

    No Known Activations