© 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. 18-GEMMASCOPE-RES-16K
    11. 8318
    Prev
    Next
    INDEX
    Explanations

    references to immune cell types and their characteristics in a medical context

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

    Hematopoietic or lymphoid cells

    np_acts-logits-general · gemini-2.0-flash

    hematologic malignancies

    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
     PCOS
    -0.53
    Bakgrunnsstoff
    -0.52
    
    -0.51
     Legendre
    -0.50
     geodesic
    -0.50
     Congrès
    -0.49
     esternos
    -0.49
     StringField
    -0.47
     Sealing
    -0.46
    {§
    -0.45
    POSITIVE LOGITS
     marrow
    0.82
     leukemia
    0.77
     lymphoma
    0.76
     Leukemia
    0.75
     autorytatywna
    0.72
     bone
    0.70
     myeloma
    0.66
    iesis
    0.65
     kasarigan
    0.65
     Marrow
    0.65
    Activations Density 1.077%

    No Known Activations