© 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. 16-GEMMASCOPE-RES-16K
    11. 8278
    Prev
    Next
    INDEX
    Explanations

    references to individuals who have held previous positions or titles, particularly in politics or public service

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

    preceding titles or positions

    np_acts-logits-general · gemini-2.0-flash

    former followed by roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [*]
    -0.72
    "}")
    -0.64
    脚注の使い方
    -0.63
    agencies
    -0.61
     mourut
    -0.60
     genoux
    -0.59
     ravens
    -0.59
     camels
    -0.59
    oxidants
    -0.58
    óngase
    -0.58
    POSITIVE LOGITS
     ex
    0.85
     Ex
    0.75
     former
    0.75
     Former
    0.66
    BeginContext
    0.63
    Former
    0.62
    ex
    0.61
    eras
    0.60
    Ex
    0.60
    ьер
    0.58
    Activations Density 0.068%

    No Known Activations