© 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. 14-GEMMASCOPE-RES-16K
    6. 11727
    Prev
    Next
    INDEX
    Explanations

    the presence of specific biological terms or jargon related to medical conditions and their diagnosis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RouterModule
    -0.72
    ⓧ
    -0.72
    principalTable
    -0.69
     חיצוניים
    -0.68
     незавершена
    -0.68
     continúas
    -0.68
     disambiguazione
    -0.65
    Portale
    -0.65
     Chwiliwch
    -0.64
    UIControlState
    -0.61
    POSITIVE LOGITS
     attualmente
    0.52
     tarko
    0.51
     hopefully
    0.51
     urma
    0.50
     atualmente
    0.49
     sahabat
    0.49
    hopefully
    0.49
     seier
    0.47
     actuellement
    0.47
     pirm
    0.47
    Activations Density 0.013%

    No Known Activations