© 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. 20-GEMMASCOPE-RES-16K
    11. 1005
    Prev
    Next
    INDEX
    Explanations

    instances of the word "worked" and other related forms, such as "work" and "working," indicating a focus on employment and career-related activities

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

    "worked" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    past employment details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
    -0.84
    StructEnd
    -0.81
    enumi
    -0.78
    ImageContext
    -0.72
    writeFieldEnd
    -0.71
    ReusableCell
    -0.71
    出版年
    -0.69
    FunctionFlags
    -0.68
    AddTagHelper
    -0.67
    UIControlState
    -0.65
    POSITIVE LOGITS
     alongside
    1.03
     in
    0.73
     together
    0.71
     abroad
    0.68
     beside
    0.65
     at
    0.61
     under
    0.61
     presso
    0.60
     Alongside
    0.57
     briefly
    0.56
    Activations Density 0.161%

    No Known Activations