© 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. 16297
    Prev
    Next
    INDEX
    Explanations

    causal relationships and temporal references within the text

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

    Sentences starting with "since"

    np_acts-logits-general · gemini-2.0-flash

    introducing a reason

    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
     الدولى
    -0.61
     تضيفلها
    -0.60
     valamint
    -0.58
    TagMode
    -0.57
    antaranya
    -0.56
     wikipagina
    -0.55
     kerana
    -0.55
     Houſe
    -0.54
     resourceCulture
    -0.54
     Schengen
    -0.53
    POSITIVE LOGITS
     it
    1.33
     they
    1.10
     there
    1.06
     we
    0.96
     surely
    0.87
     nobody
    0.86
     this
    0.85
     ultimately
    0.82
     the
    0.81
     most
    0.80
    Activations Density 0.263%

    No Known Activations