© 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. 4532
    Prev
    Next
    INDEX
    Explanations

    terms related to challenges and difficulties in scientific or medical contexts

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

    Comes before reasons or justifications

    np_acts-logits-general · gemini-2.0-flash

    due to difficult outcomes

    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
    migrationBuilder
    -0.91
    __*/
    -0.77
    DockStyle
    -0.76
     فريبيس
    -0.75
    :✨
    -0.75
    nloa
    -0.74
    sizeCache
    -0.73
     ProtoMessage
    -0.72
    enumi
    -0.71
    webElementXpaths
    -0.71
    POSITIVE LOGITS
     due
    3.32
    due
    2.85
     debido
    2.58
     devido
    2.53
    Due
    2.50
     Due
    2.46
     DUE
    2.40
     owing
    2.33
     vanwege
    2.09
     بسبب
    2.08
    Activations Density 1.265%

    No Known Activations