© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 5491
    Prev
    Next
    INDEX
    Explanations

    architectural features and details related to buildings, particularly cathedrals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.81
    MigrationBuilder
    -0.78
    RegressionTest
    -0.72
    ValueGenerated
    -0.68
     Wikimedijinoj
    -0.68
    verwijspagina
    -0.65
    Jeografia
    -0.62
     estekak
    -0.62
     informée
    -0.61
    WithIOException
    -0.58
    POSITIVE LOGITS
     entrance
    0.83
     corridor
    0.83
     vestibule
    0.82
     walkway
    0.79
     platform
    0.77
     aisles
    0.76
     platforms
    0.76
     foyer
    0.76
     passage
    0.76
     aisle
    0.75
    Activations Density 0.231%

    No Known Activations