© 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. 2-GEMMASCOPE-RES-16K
    11. 2483
    Prev
    Next
    INDEX
    Explanations

    references to specific places and names, particularly those related to the context of St. Mary and St. Anne

    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
     []:
    -0.51
    core
    -0.50
    })$}
    -0.45
    </h1>
    -0.41
     mergeFrom
    -0.40
     core
    -0.40
    </strong>
    -0.39
    Core
    -0.38
    ']")
    -0.38
    لكتر
    -0.38
    POSITIVE LOGITS
     Italijanski
    0.73
    Jeografia
    0.67
    ^(@)
    0.67
    +:+
    0.65
     Creek
    0.65
    InteropServices
    0.65
    idemia
    0.64
     CREEK
    0.63
    WireFormatLite
    0.63
     BoxFit
    0.62
    Activations Density 1.737%

    No Known Activations