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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15713
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Gu" and its variations, likely related to references or topics concerning a specific subject or location

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

    Starts with "Gu" and is often followed by a vowel

    np_acts-logits-general · gemini-2.0-flash

    gu- prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     שוליים
    -0.72
     autorytatywna
    -0.69
     الحره
    -0.68
    AndEndTag
    -0.65
    DotNetBar
    -0.64
    ObjectContext
    -0.63
     MessageBoxIcon
    -0.61
    出版年
    -0.59
     bezeichneter
    -0.58
     AssemblyTitle
    -0.57
    POSITIVE LOGITS
    Gu
    0.81
     Gu
    0.74
     GU
    0.68
     gu
    0.61
     Guin
    0.59
     Gué
    0.59
     Guth
    0.57
     Guine
    0.53
     Guar
    0.52
    Guar
    0.52
    Activations Density 0.070%

    No Known Activations