© 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. 8489
    Prev
    Next
    INDEX
    Explanations

    references to Poland and its regions, particularly related to Polish identity and culture

    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
     Monfieur
    -1.25
     himſelf
    -1.02
     themſelves
    -1.02
     uſed
    -1.01
     ſche
    -1.00
     myſelf
    -0.99
     Theſe
    -0.98
     Jefus
    -0.96
     pleaſure
    -0.95
     Efq
    -0.94
    POSITIVE LOGITS
     jest
    0.95
     estekak
    0.83
    Portale
    0.78
     Nie
    0.72
    )':
    0.72
    ništvo
    0.71
     są
    0.69
     Mate
    0.68
    ł
    0.67
    DispatchToProps
    0.65
    Activations Density 0.016%

    No Known Activations