Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4519
    Prev
    Next
    INDEX
    Explanations

    specific proteins and cellular interactions related to immune responses

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

    cells, especially infected or cultured cells

    np_acts-logits-general · gemini-2.0-flash

    types of cells and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=",
    -0.63
    tonsoft
    -0.60
    setVerticalGroup
    -0.60
    IntentFilter
    -0.53
    mybatisplus
    -0.51
    typeorm
    -0.50
     surla
    -0.49
    SequentialGroup
    -0.49
    '])){
    
    -0.48
    ExtendWith
    -0.48
    POSITIVE LOGITS
     cells
    1.28
    cells
    0.90
     Cells
    0.83
     CELLS
    0.76
     cellules
    0.74
    ocytes
    0.73
     neurons
    0.73
    Cells
    0.71
    cytes
    0.67
     erythrocytes
    0.67
    Activations Density 1.336%

    No Known Activations