© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 16009
    Prev
    Next
    INDEX
    Explanations

    references to historical churches and their architectural significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns and place names, particularly locations and geographic regions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.58
    complexType
    -0.54
    HtmlAttribute
    -0.51
    runApp
    -0.49
     EconPapers
    -0.48
    writeFieldEnd
    -0.47
    IntoConstraints
    -0.47
    ImageContext
    -0.46
    principalColumn
    -0.44
    MigrationBuilder
    -0.43
    POSITIVE LOGITS
     Lincolnshire
    0.70
     Nottingham
    0.59
     Lincoln
    0.58
    Lincoln
    0.56
    Nottingham
    0.55
     Nebraska
    0.51
     LINCOLN
    0.50
    Nebraska
    0.50
    Lin
    0.47
     lincoln
    0.46
    Activations Density 0.196%

    No Known Activations