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. 9-GEMMASCOPE-RES-131K
    6. 7845
    Prev
    Next
    INDEX
    Explanations

    Japanese sentence-ending particles and phrases indicating actions or states

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

    -te conjugations

    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
     Patro
    -0.36
     oignons
    -0.36
     setTitle
    -0.35
    +#+#
    -0.35
     newState
    -0.35
     reen
    -0.33
    DataSetChanged
    -0.33
     jsonArray
    -0.33
     "#"
    -0.33
    \{\\
    -0.32
    POSITIVE LOGITS
    しくて
    0.90
    があって
    0.81
    くて
    0.80
    あって
    0.78
    していて
    0.77
    されていて
    0.74
    っていて
    0.73
    なくて
    0.72
    いて
    0.68
    もあって
    0.61
    Activations Density 0.006%

    No Known Activations