© 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. 8-GEMMASCOPE-RES-16K
    11. 5299
    Prev
    Next
    INDEX
    Explanations

    elements related to medical test results and personal health metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſind
    -1.09
     ་་
    -0.98
     iſt
    -0.95
    ]),
    -0.93
    </caption>
    -0.92
    .³
    -0.89
    .",
    -0.89
     itſelf
    -0.86
     ―――――
    -0.85
    ſelf
    -0.85
    POSITIVE LOGITS
     stuff
    1.07
     I
    0.91
     nice
    0.88
     maybe
    0.87
     crappy
    0.87
     kinda
    0.86
     mierda
    0.83
     my
    0.83
     Maybe
    0.82
     thingy
    0.82
    Activations Density 3.213%

    No Known Activations