© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 244
    Prev
    Next
    INDEX
    Explanations

    medical terms related to specific diseases and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Disease severity or progression

    np_acts-logits-general · gemini-2.0-flash

    disease severity and progression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antiseptic
    -0.48
     Pis
    -0.45
    Pis
    -0.45
    pis
    -0.45
    bu
    -0.44
    gar
    -0.43
    ंत
    -0.43
    ken
    -0.43
     mát
    -0.42
    ịp
    -0.42
    POSITIVE LOGITS
     severity
    1.05
     progression
    0.98
    ########.
    0.93
    OGND
    0.90
     Progression
    0.90
    Progression
    0.89
     Severity
    0.86
    InjectAttribute
    0.85
    StructEnd
    0.82
    severity
    0.81
    Activations Density 1.168%

    No Known Activations