© 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. 17-GEMMASCOPE-RES-16K
    11. 11671
    Prev
    Next
    INDEX
    Explanations

    references to geographical or location-specific entities and names, particularly related to "Milton" and "Dawson Springs."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .}}
    -0.78
     connus
    -0.75
     colorés
    -0.71
     Theſe
    -0.69
     estekak
    -0.65
    Hentet
    -0.65
     inconn
    -0.64
     privées
    -0.63
     scolaires
    -0.63
     pregi
    -0.63
    POSITIVE LOGITS
    “-
    0.58
    ylvanian
    0.56
    姓
    0.53
    manian
    0.52
    neapolis
    0.51
     Rég
    0.51
    +#+#
    0.50
    بالإنجليزية
    0.50
    ashian
    0.50
    roth
    0.49
    Activations Density 0.947%

    No Known Activations