© 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. 10474
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the existence or characteristics of an entity

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

    Sentences starting with "It" followed by certain verbs

    np_acts-logits-general · gemini-2.0-flash

    It is

    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
    SharedDtor
    -0.79
     ProtoMessage
    -0.73
    ukone
    -0.72
     Савезне
    -0.71
     esternos
    -0.63
    Jeografia
    -0.62
    ///</
    -0.57
     nonUne
    -0.57
    لينكات
    -0.55
    BufferException
    -0.54
    POSITIVE LOGITS
     kaynağından
    0.61
    ModelAdmin
    0.50
    itself
    0.50
    kenstock
    0.48
     depends
    0.47
    QMetaType
    0.47
     itself
    0.47
    Reducers
    0.46
     Appleton
    0.46
     works
    0.45
    Activations Density 0.040%

    No Known Activations