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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 14898
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to medical diagnosis and assessment

    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
    +#+#
    -0.82
    клопе
    -0.76
    openhauer
    -0.74
    vereignty
    -0.72
     piede
    -0.72
     cellulare
    -0.72
    AnimationsModule
    -0.71
     supérieurs
    -0.71
     resistenza
    -0.69
     unirse
    -0.68
    POSITIVE LOGITS
     diagnosis
    2.37
     diagnose
    2.23
     diagnoses
    2.18
     Diagnosis
    2.04
     diagnosing
    2.02
    diagnosis
    2.01
     Diagnos
    1.90
     DIAG
    1.89
     diagnosed
    1.88
     Diagnose
    1.82
    Activations Density 0.138%

    No Known Activations