© 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. 1609
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize totality or inclusiveness, particularly in relation to items or groups

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

    "all" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    all

    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
     DIT
    -0.52
    InputTagHelper
    -0.45
    说是
    -0.45
    MultipartFile
    -0.45
    buc
    -0.43
    insch
    -0.43
     Italijani
    -0.43
     Psychiat
    -0.43
    bag
    -0.43
     уго
    -0.43
    POSITIVE LOGITS
     모든
    0.76
     wszystkich
    0.68
     tüm
    0.66
     semua
    0.64
     mọi
    0.63
    全ての
    0.62
     wszystkie
    0.62
    すべての
    0.62
    所有
    0.60
     所有
    0.60
    Activations Density 0.249%

    No Known Activations