© 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. 27-GEMMASCOPE-RES-16K
    11. 9989
    Prev
    Next
    INDEX
    Explanations

    terms related to historical preservation and local history institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pareto
    -0.38
     Montaigne
    -0.37
     metast
    -0.35
     calms
    -0.35
     Davos
    -0.35
    人民共和国
    -0.35
     med
    -0.34
     inversely
    -0.34
     pumped
    -0.34
     chop
    -0.34
    POSITIVE LOGITS
     historians
    1.23
     historian
    1.16
     historiador
    1.11
     Historian
    1.00
     historical
    0.98
     Historical
    0.95
    Historical
    0.93
     archival
    0.93
     Historic
    0.91
    historical
    0.88
    Activations Density 0.555%

    No Known Activations