© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13044
    Prev
    Next
    INDEX
    Explanations

    references to relationships and personal priorities

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

    the word "first"

    np_acts-logits-general · gemini-2.0-flash

    being the first

    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
    RectangleBorder
    -0.68
    Билгалдахарш
    -0.63
    Lähteet
    -0.63
    MessageTagHelper
    -0.60
    ParallelGroup
    -0.60
     ExecuteAsync
    -0.59
    migrationBuilder
    -0.59
     ""],
    -0.57
    Trama
    -0.56
    SizeF
    -0.56
    POSITIVE LOGITS
     first
    2.75
    first
    2.42
     zuerst
    2.18
     primero
    2.14
     terlebih
    2.06
     först
    1.97
     først
    1.96
     FIRST
    1.93
     primeiro
    1.92
    First
    1.91
    Activations Density 0.496%

    No Known Activations