© 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. 15-GEMMASCOPE-RES-16K
    11. 2540
    Prev
    Next
    INDEX
    Explanations

    references to medical treatment and health-related outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.78
     utafitiHapana
    -0.78
    Personendaten
    -0.76
     Савезне
    -0.73
    tagHelperRunner
    -0.73
    ValueStyle
    -0.71
     autorytatywna
    -0.70
    awtextra
    -0.69
     protoimpl
    -0.69
    
    -0.68
    POSITIVE LOGITS
     dårlig
    0.52
     dår
    0.52
     neglect
    0.46
     failings
    0.44
     lapses
    0.43
     inadequate
    0.43
     lemah
    0.43
     weak
    0.42
     weaknesses
    0.41
     Falta
    0.40
    Activations Density 0.695%

    No Known Activations