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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 22959
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases that indicate essential items or concepts in various contexts, including assets, technology, and social discussions

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

    large or big modifiers

    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
     murni
    -0.41
     gesteld
    -0.40
     marginally
    -0.40
     slight
    -0.40
     isolato
    -0.39
     medy
    -0.39
     voegen
    -0.38
    AxisAlignment
    -0.38
     hemel
    -0.38
    ティック
    -0.38
    POSITIVE LOGITS
    Large
    0.88
     big
    0.88
    Huge
    0.84
     Large
    0.84
    large
    0.83
     large
    0.80
     Huge
    0.78
    big
    0.77
    LARGE
    0.75
    Big
    0.75
    Activations Density 0.112%

    No Known Activations