© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7157
    Prev
    Next
    INDEX
    Explanations

    terms related to specific biological markers or medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arithmic
    -0.85
    $
    
    -0.85
     Eichen
    -0.84
    iosync
    -0.83
     TDS
    -0.82
    "]=
    -0.81
    "]
    
    -0.81
     ")[
    -0.80
     Gladstone
    -0.79
     tchèque
    -0.77
    POSITIVE LOGITS
     Bertha
    0.92
     convite
    0.84
     Berkshire
    0.83
    ///</
    0.79
     Berk
    0.76
     Burk
    0.76
    IBOutlet
    0.75
     Peralta
    0.73
     ceinture
    0.73
    wand
    0.72
    Activations Density 1.488%

    No Known Activations