© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28440
    Prev
    Next
    INDEX
    Explanations

    specific biochemical processes and interactions, particularly involving proteins and receptors

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

    hemocytes, helix, crystals, acid, iodide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     occurred
    -0.53
     happening
    -0.47
     averted
    -0.47
     culminated
    -0.46
     ensued
    -0.46
     affirming
    -0.46
     contradicted
    -0.45
    rific
    -0.44
    tra
    -0.44
     happened
    -0.44
    POSITIVE LOGITS
    ContentAsync
    1.13
    DockStyle
    1.01
    Espèce
    0.91
    findpost
    0.76
    -------------</
    0.73
     myſelf
    0.73
    ponses
    0.72
     themſelves
    0.69
     يتيمه
    0.68
    parsedMessage
    0.68
    Activations Density 0.404%

    No Known Activations