© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 11697
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to tumors and cancer treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.54
    HtmlAttribute
    -0.51
    Sucesor
    -0.51
     nakalista
    -0.50
    Havolalar
    -0.47
     населення
    -0.42
     GetEnumerator
    -0.42
    uesia
    -0.41
    Населення
    -0.41
    toMatchSnapshot
    -0.41
    POSITIVE LOGITS
     mice
    1.34
     rats
    1.13
     mouse
    1.10
     Mice
    1.09
    Mice
    1.02
    mice
    0.97
     souris
    0.95
     animals
    0.91
     Rats
    0.90
     Mouse
    0.89
    Activations Density 2.326%

    No Known Activations