© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15738
    Prev
    Next
    INDEX
    Explanations

    terms related to medical indicators and kidney disease

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

    Followed by "of the" or "is a/an"

    np_acts-logits-general · gemini-2.0-flash

    one of the most important

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     эти
    -0.50
    UnusedPrivate
    -0.49
     magari
    -0.47
    this
    -0.45
     poszczegól
    -0.43
     cober
    -0.43
     eventualmente
    -0.43
     these
    -0.42
     this
    -0.41
     lainnya
    -0.41
    POSITIVE LOGITS
     major
    0.85
     very
    0.80
     chi̍t
    0.78
     important
    0.75
     Audiodateien
    0.73
     تانيه
    0.71
     among
    0.71
     parmi
    0.71
     biggest
    0.70
    หนึ่ง
    0.70
    Activations Density 0.176%

    No Known Activations