© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1603
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize collaboration or assistance in achieving goals

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

    Following the word "with"

    np_acts-logits-general · gemini-2.0-flash

    with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     Bek
    -0.36
     main
    -0.34
    InitStruct
    -0.34
     Schlä
    -0.34
    QRST
    -0.33
     belongs
    -0.32
     Scuola
    -0.32
     share
    -0.32
    ServiceTest
    -0.32
     belong
    -0.31
    POSITIVE LOGITS
     للاسماء
    0.79
    With
    0.61
    HasAnnotation
    0.60
    AndEndTag
    0.59
     nahilalakip
    0.58
    InputBorder
    0.57
    TagMode
    0.57
     With
    0.55
    migrationBuilder
    0.54
     AssemblyTitle
    0.54
    Activations Density 0.225%

    No Known Activations