Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1510
    Prev
    Next
    INDEX
    Explanations

    references to the term "Gu" in various contexts, particularly in relation to people or places

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

    words starting with Gu

    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
    caso
    -0.48
     Addams
    -0.48
    roses
    -0.48
    iores
    -0.47
    linky
    -0.46
    Basics
    -0.45
     Nachbar
    -0.45
     Morelos
    -0.45
    aps
    -0.44
    datei
    -0.44
    POSITIVE LOGITS
     Gu
    1.09
    Gu
    1.05
     gu
    1.00
     GU
    0.98
    gu
    0.92
     Guille
    0.86
    GU
    0.83
     Guernsey
    0.81
    guint
    0.79
     Guill
    0.76
    Activations Density 0.012%

    No Known Activations