© 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. 22-GEMMASCOPE-RES-16K
    11. 14862
    Prev
    Next
    INDEX
    Explanations

    terms related to specific types of blood disorders, particularly leukemia and its characteristics

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

    Leukemia, bone marrow, and related hematologic neoplasms

    np_acts-logits-general · gemini-2.0-flash

    blood and marrow leukemia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.59
    KeySpec
    -0.50
    pulumi
    -0.45
    iprot
    -0.42
     Coral
    -0.41
     Kah
    -0.41
    setContentView
    -0.40
    codable
    -0.40
    uanto
    -0.40
     Sonn
    -0.40
    POSITIVE LOGITS
     bone
    1.00
     leukemia
    0.98
     hemato
    0.98
     marrow
    0.97
     Leukemia
    0.91
    Leuk
    0.88
     leuk
    0.87
     myeloid
    0.86
     Leuk
    0.86
     myel
    0.86
    Activations Density 1.153%

    No Known Activations