© 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 EvalsExportsinterp-engineNEWAPI 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. 9742
    Prev
    Next
    INDEX
    Explanations

    terms related to medical risk factors and health conditions

    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
    发表于
    -0.45
     humains
    -0.43
    hopefully
    -0.42
    ✭✭
    -0.41
     Hopefully
    -0.40
    Ĝ
    -0.40
    raulic
    -0.40
    Hopefully
    -0.39
     menschliche
    -0.39
    SBATCH
    -0.38
    POSITIVE LOGITS
     smoking
    0.77
     previous
    0.71
     history
    0.67
     tobacco
    0.66
     Smoking
    0.66
    Previous
    0.65
     Previous
    0.63
     preexisting
    0.62
     comor
    0.62
    previous
    0.61
    Activations Density 1.633%

    No Known Activations