© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15687
    Prev
    Next
    INDEX
    Explanations

    the presence of ampersands (&)

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

    The ampersand symbol (&)

    np_acts-logits-general · gemini-2.0-flash

    lists separated by &

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -0.49
    .")
    -0.42
     hemo
    -0.41
    )">
    -0.40
    {}",
    -0.39
     Widodo
    -0.39
     Sink
    -0.39
    ())))
    -0.39
     sink
    -0.38
     pio
    -0.38
    POSITIVE LOGITS
     &
    1.02
     \&
    0.90
    &
    0.74
     $\&$
    0.73
    \&
    0.73
     Affiliations
    0.69
     [&
    0.67
     and
    0.66
     '&
    0.66
     &\
    0.65
    Activations Density 0.085%

    No Known Activations