© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5248
    Prev
    Next
    INDEX
    Explanations

    references to Boston and its various associations, particularly in relation to crime and film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.98
     Monfieur
    -0.79
    Дереккөздер
    -0.79
    Clik
    -0.76
    zsche
    -0.74
    fireEvent
    -0.74
    aarrggbb
    -0.73
     Diſ
    -0.72
    Alamat
    -0.71
    Rüyada
    -0.70
    POSITIVE LOGITS
     Massachusetts
    1.53
    Massachusetts
    1.41
    BOSTON
    1.41
     Boston
    1.40
    Boston
    1.32
     BOSTON
    1.15
    boston
    1.08
     MASSACHUSETTS
    1.04
     boston
    1.04
     Celtics
    1.02
    Activations Density 0.493%

    No Known Activations