© 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. 9-GEMMASCOPE-RES-131K
    11. 12703
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "dozen" and its variations

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

    dozen of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spirituelle
    -0.47
     larmes
    -0.45
    Silvia
    -0.45
     âmes
    -0.43
     Aéroport
    -0.41
     juges
    -0.41
     magnétique
    -0.41
    aerop
    -0.41
    Frontend
    -0.41
     என்ற
    -0.41
    POSITIVE LOGITS
     dozen
    1.97
    dozen
    1.73
     dozens
    1.47
     handful
    1.00
     dezen
    0.87
    zens
    0.86
     decenas
    0.83
     dizaine
    0.81
     numerous
    0.79
    Hundred
    0.75
    Activations Density 0.002%

    No Known Activations