© 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. 24-GEMMASCOPE-RES-16K
    11. 13638
    Prev
    Next
    INDEX
    Explanations

    references to legislative or political figures, particularly those with the title "Senator."

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

    starting with "Sen" followed by suffixes

    np_acts-logits-general · gemini-2.0-flash

    Sen. and sensibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ///</
    -0.60
     gainera
    -0.56
     sério
    -0.55
    omeness
    -0.54
    adaptiveStyles
    -0.52
     PropTypes
    -0.49
    PROPS
    -0.48
    putra
    -0.47
    NUMX
    -0.46
    UnknownFieldSet
    -0.45
    POSITIVE LOGITS
    ParallelGroup
    0.66
    
    0.59
    yarnpkg
    0.56
    powiedz
    0.54
     uintptr
    0.52
    sible
    0.52
    subpackage
    0.51
    ecore
    0.51
    VersionUID
    0.50
    ussi
    0.50
    Activations Density 0.146%

    No Known Activations