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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 95235
    Prev
    Next
    INDEX
    Explanations

    constructs related to pairs and tuples in programming or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    melen
    -0.37
    Bul
    -0.35
    ChromeDriver
    -0.35
    bul
    -0.34
     defences
    -0.34
    cabul
    -0.34
     obro
    -0.34
    躇
    -0.33
    media
    -0.33
     bul
    -0.33
    POSITIVE LOGITS
     JAXBElement
    0.65
     pairs
    0.61
     tuple
    0.61
     Pair
    0.60
     pairing
    0.60
    yntaxException
    0.60
     pair
    0.59
     Мексичка
    0.58
     between
    0.58
    Pair
    0.57
    Activations Density 0.051%

    No Known Activations