© 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. 7989
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "there" in various contexts

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

    "there is" or "there are"

    np_acts-logits-general · gemini-2.0-flash

    existence of something

    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
    tagext
    -0.86
     EconPapers
    -0.85
     TextAppearance
    -0.74
    PreferredItem
    -0.72
    DockStyle
    -0.70
     invokingState
    -0.70
    ScopeManager
    -0.70
    BeginContext
    -0.68
    HtmlAttribute
    -0.66
    medriver
    -0.65
    POSITIVE LOGITS
     is
    1.04
     are
    1.00
     was
    0.68
     were
    0.68
     exists
    0.64
     isn
    0.59
     aren
    0.58
    คือ
    0.55
    inafter
    0.54
     ARE
    0.52
    Activations Density 0.138%

    No Known Activations