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. 1453
    Prev
    Next
    INDEX
    Explanations

    references to tabulation and tab-related concepts

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

    "Tab" followed by numbers or table references

    np_acts-logits-general · gemini-2.0-flash

    table or tabulating

    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
    ondissement
    -0.53
     progre
    -0.51
    tero
    -0.49
    <%=
    -0.49
    ✋
    -0.48
    ródła
    -0.48
    脚注の使い方
    -0.48
    lition
    -0.47
    menge
    -0.47
    ếc
    -0.46
    POSITIVE LOGITS
     tab
    1.08
     Tab
    1.04
     tabs
    1.03
    Tab
    0.96
     Tabs
    0.94
     TAB
    0.91
    TAB
    0.86
    tab
    0.79
     Tabor
    0.79
     myſelf
    0.77
    Activations Density 0.044%

    No Known Activations