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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 8170
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations related to healthcare, research, and clinical studies

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

    Acronyms followed by a parenthesis

    np_acts-logits-general · gemini-2.0-flash

    acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.63
     }}$}
    -0.53
    DisplayMode
    -0.53
    "])
    
    -0.52
     but
    -0.51
    ...)
    -0.50
     shared
    -0.50
     pinulongan
    -0.49
    PreferredItem
    -0.49
     and
    -0.49
    POSITIVE LOGITS
     hereafter
    0.82
     genannt
    0.81
     genoemd
    0.78
     henceforth
    0.71
     CURIAM
    0.70
     hereinafter
    0.66
     vélos
    0.65
     hänen
    0.64
     étoit
    0.62
     siglas
    0.62
    Activations Density 0.283%

    No Known Activations