© 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. 16378
    Prev
    Next
    INDEX
    Explanations

    terms related to infecting and disinfecting processes

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

    followed by "-ing" suffix

    np_acts-logits-general · gemini-2.0-flash

    prohibiting, harnessing, infecting, employing

    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
     latter
    -0.97
     Carlin
    -0.88
    🔥🔥
    -0.88
    mmation
    -0.87
     restTemplate
    -0.83
    ist
    -0.82
     Maren
    -0.77
     webdriver
    -0.76
    ogeneous
    -0.76
    Rcpp
    -0.74
    POSITIVE LOGITS
    ing
    2.95
    ING
    2.17
    ingi
    1.17
    ingh
    1.08
    ة
    1.05
    ingan
    1.03
    ingl
    1.02
    ingar
    1.00
    ging
    0.98
    ingin
    0.98
    Activations Density 1.367%

    No Known Activations