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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12737
    Prev
    Next
    INDEX
    Explanations

    references to historical events and themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.57
    writeFieldEnd
    -0.54
    Geplaatst
    -0.52
    ActionCreators
    -0.52
    exitRule
    -0.51
    AccessorTable
    -0.50
    AddTagHelper
    -0.50
    Vidite
    -0.48
    TestBed
    -0.48
    يميديا
    -0.48
    POSITIVE LOGITS
     historical
    1.16
     history
    1.03
     Historical
    0.98
     History
    0.95
    Historical
    0.94
    History
    0.94
     historic
    0.93
     historians
    0.91
     HISTORICAL
    0.89
    history
    0.86
    Activations Density 0.594%

    No Known Activations