© 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. 17-GEMMASCOPE-RES-16K
    6. 11424
    Prev
    Next
    INDEX
    Explanations

    terms related to health and medical conditions, specifically focusing on treatments and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षाओं
    -0.65
     Amalgam
    -0.60
     anthracite
    -0.59
     AssemblyCompany
    -0.56
     goldfish
    -0.56
     bivolt
    -0.56
     Rooster
    -0.55
     crickets
    -0.54
     Nicholls
    -0.53
     Palt
    -0.53
    POSITIVE LOGITS
     adaptations
    0.78
    +#+#
    0.63
     adaptation
    0.57
     kaarangay
    0.54
     especializada
    0.54
     specialized
    0.54
     estrategias
    0.53
     adap
    0.51
    antart
    0.51
     specialization
    0.50
    Activations Density 0.867%

    No Known Activations