© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5434
    Prev
    Next
    INDEX
    Explanations

    reference to chronic diseases

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

    "chronic" followed by a medical condition

    np_acts-logits-general · gemini-2.0-flash

    chronic medical conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تيجة
    -0.76
    Geplaatst
    -0.66
     DevExpress
    -0.64
    moiselle
    -0.62
     DialogResult
    -0.60
     Vorsitzender
    -0.60
     Préférences
    -0.60
     Autorizaciones
    -0.59
    TemporalType
    -0.59
     avvic
    -0.58
    POSITIVE LOGITS
    ling
    0.62
     Spraw
    0.59
    UpInside
    0.58
    CastException
    0.54
    IUrlHelper
    0.50
    led
    0.49
    IZONTAL
    0.49
     Batch
    0.48
    les
    0.47
    entrant
    0.47
    Activations Density 0.130%

    No Known Activations