© 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 - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2110
    Prev
    Next
    INDEX
    Explanations

    references to significant events or milestones related to people or organizations

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

    Names after conjunctions or prepositions

    np_acts-logits-general · gemini-2.0-flash

    last name

    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
    ChildScrollView
    -0.62
    よいよ
    -0.52
     AssemblyTitle
    -0.47
     @"/
    -0.46
     ordinance
    -0.46
    ScreenState
    -0.45
    तान
    -0.45
     contrário
    -0.43
     galite
    -0.43
    novel
    -0.43
    POSITIVE LOGITS
     незавершена
    0.79
     >=",
    0.75
     fellow
    0.69
    GeneratedValue
    0.65
     former
    0.65
     Савезне
    0.64
     dAtA
    0.63
    fellow
    0.60
    writeFieldEnd
    0.60
    TintMode
    0.59
    Activations Density 0.344%

    No Known Activations