© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 7633
    Prev
    Next
    INDEX
    Explanations

    keywords related to coagulation and bleeding disorders in clinical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.65
    corrhi
    -0.61
    Obrázky
    -0.61
    íncia
    -0.59
     Hadrian
    -0.59
    AnimationsModule
    -0.59
     monotonic
    -0.58
     scopes
    -0.58
    epa
    -0.58
     Immort
    -0.57
    POSITIVE LOGITS
     clots
    1.04
     clotting
    0.99
     throm
    0.98
     thrombosis
    0.97
    throm
    0.93
     thrombo
    0.93
     clot
    0.91
     Throm
    0.87
     anticoag
    0.86
     coagulation
    0.81
    Activations Density 0.982%

    No Known Activations