© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104256
    Prev
    Next
    INDEX
    Explanations

    technical terms and procedures related to surgery and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     müſſen
    -0.85
     utafitiHapana
    -0.81
     verſch
    -0.81
    transQ
    -0.79
    Espèce
    -0.79
    <unused41>
    -0.79
    <unused74>
    -0.79
     snippetHide
    -0.79
    <unused47>
    -0.79
    <unused43>
    -0.79
    POSITIVE LOGITS
     až
    0.27
     Berücksich
    0.25
     investasi
    0.25
     renk
    0.24
     pré
    0.24
     flotante
    0.24
    ించ
    0.23
     alent
    0.23
     cedo
    0.22
     bancada
    0.22
    Activations Density 0.297%

    No Known Activations