© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 95824
    Prev
    Next
    INDEX
    Explanations

    elements of understanding and connections between concepts and entities

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

    unwittingly or unknowingly acted

    np_acts-logits-general · gemini-2.5-flash-lite

    words indicating knowledge, awareness, or possession (e.g., told/informed, know/remember, possessed/disseminated).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     AssemblyCompany
    -0.57
    Litteratur
    -0.46
     naturais
    -0.46
    ftagPool
    -0.46
    windowFixed
    -0.46
     treno
    -0.45
     SafeMath
    -0.44
     <<<<<<<<<<<<<<
    -0.44
     ferrovi
    -0.43
     scienza
    -0.43
    POSITIVE LOGITS
    forChild
    0.37
    Życiorys
    0.36
     unwittingly
    0.35
     unknowingly
    0.35
     should
    0.33
     unconsciously
    0.33
    endforeach
    0.33
     ness
    0.32
    在外
    0.32
     ultimately
    0.32
    Activations Density 0.106%

    No Known Activations