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. 1-GEMMASCOPE-RES-16K
    6. 13610
    Prev
    Next
    INDEX
    Explanations

    references to tumor necrosis factor and other inflammatory markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "):
    
    -0.68
     sumpay
    -0.66
    matchCondition
    -0.65
    GraphicsUnit
    -0.65
    SizeMode
    -0.63
     ComVisible
    -0.62
    addLast
    -0.61
    AccessorTable
    -0.61
     parseFrom
    -0.60
    SourceChecksum
    -0.59
    POSITIVE LOGITS
    alpha
    4.23
     alpha
    3.90
    Alpha
    3.40
     Alpha
    3.37
    α
    3.12
     α
    2.96
     ALPHA
    2.90
    ALPHA
    2.89
     alfa
    2.51
    
    2.32
    Activations Density 0.260%

    No Known Activations