© 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. 3-GEMMASCOPE-RES-16K
    11. 8736
    Prev
    Next
    INDEX
    Explanations

    references to political parties, particularly the GOP (Republican Party)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.56
     AssemblyProduct
    -0.45
    INCREF
    -0.44
    بالإنجليزية
    -0.39
    tinyos
    -0.39
     utafitiHapana
    -0.38
    WithMany
    -0.38
    mTitle
    -0.37
    tagext
    -0.37
    CRP
    -0.37
    POSITIVE LOGITS
    tagHelperRunner
    0.92
    featureID
    0.86
     jLabel
    0.80
    帖最后由
    0.71
    GenerationType
    0.71
    AutoresizingMask
    0.68
    contentLoaded
    0.68
    StackNavigator
    0.66
     Vân
    0.66
    transQ
    0.65
    Activations Density 0.419%

    No Known Activations