© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 22936
    Prev
    Next
    INDEX
    Explanations

    occurrences and references to subsets in mathematical or logical contexts

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

    subset of items

    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
    ếng
    -0.45
     Larry
    -0.41
     jSON
    -0.41
     mengh
    -0.39
     lavori
    -0.39
     mengajar
    -0.38
    MemoryWarning
    -0.38
     schoenen
    -0.37
     Bea
    -0.37
     Paul
    -0.37
    POSITIVE LOGITS
     subset
    1.19
    Subset
    0.99
    subset
    0.96
     subsets
    0.94
    subsets
    0.90
    subseteq
    0.69
     betweenstory
    0.66
    ⊂
    0.65
     subtype
    0.64
     portion
    0.63
    Activations Density 0.021%

    No Known Activations