© 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. 891
    Prev
    Next
    INDEX
    Explanations

    references to power dynamics and responsibilities in organizational or social contexts

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

    Text after function words or names

    np_acts-logits-general · gemini-2.0-flash

    initiating actions or events

    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
     CreateTagHelper
    -0.90
    TypedDataSet
    -0.87
    HasForeignKey
    -0.81
     Lightboxes
    -0.75
    WebVitals
    -0.73
     snippetHide
    -0.72
     '\\;'
    -0.72
     PyLong
    -0.70
    whenever
    -0.69
     GeoNames
    -0.69
    POSITIVE LOGITS
     xong
    0.57
     очеред
    0.56
     nanti
    0.54
    才知道
    0.50
     realizes
    0.46
     initiale
    0.46
     berlangsung
    0.44
     begins
    0.43
    初めて
    0.43
    cipes
    0.43
    Activations Density 0.433%

    No Known Activations