© 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. 57644
    Prev
    Next
    INDEX
    Explanations

    moments of personal storytelling and emotional reflection

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

    that followed by things

    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-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
    wapV
    -0.38
    有所
    -0.35
     lunettes
    -0.33
    VYMaps
    -0.33
     First
    -0.33
    tagHelperRunner
    -0.33
     comput
    -0.32
     download
    -0.32
    不是很
    -0.32
    testnet
    -0.31
    POSITIVE LOGITS
     addirittura
    0.66
     jopa
    0.62
     persino
    0.61
     literalmente
    0.58
     Grüsse
    0.57
    Bahkan
    0.57
     zelfs
    0.57
    contentLoaded
    0.57
     termica
    0.56
     sogar
    0.55
    Activations Density 0.066%

    No Known Activations