© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 58608
    Prev
    Next
    INDEX
    Explanations

    structured data or numeric values often related to measurements

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

    Donna names

    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
    exitRule
    -0.85
     EconPapers
    -0.84
     autorytatywna
    -0.75
    DoubleQuotes
    -0.73
    AnchorTagHelper
    -0.73
    GOTREF
    -0.72
     AssemblyCompany
    -0.71
     NSCoder
    -0.69
     AppCompatTheme
    -0.69
    AddTagHelper
    -0.69
    POSITIVE LOGITS
    무
    0.31
     
    0.30
    <eos>
    0.30
    ↵
    0.29
     gibi
    0.29
    antd
    0.28
    ecma
    0.28
    ,
    0.28
     match
    0.28
     account
    0.28
    Activations Density 0.017%

    No Known Activations