© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8768
    Prev
    Next
    INDEX
    Explanations

    terms related to dilution protocols and sample preparation in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sécher
    -0.54
    श्यक
    -0.52
     École
    -0.49
     Erl
    -0.49
     rito
    -0.49
    ără
    -0.48
    łuż
    -0.48
    spesies
    -0.48
    presidente
    -0.47
    genos
    -0.47
    POSITIVE LOGITS
    
    0.73
     Chwiliwch
    0.69
     intptr
    0.68
    ChildScrollView
    0.67
     diluted
    0.67
    Datuak
    0.66
    UIControlState
    0.66
     CK
    0.61
     désolés
    0.59
    gatsby
    0.57
    Activations Density 2.840%

    No Known Activations