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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 18880
    Prev
    Next
    INDEX
    Explanations

    phrases indicating recognition or celebration of significant events and achievements

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

    celebrate, honor, remember

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Inspect
    -0.30
     develops
    -0.27
    Explicación
    -0.26
    管
    -0.26
    Explanation
    -0.26
     Improvement
    -0.26
    ichtung
    -0.26
     Conferencia
    -0.26
     manip
    -0.25
     desenvol
    -0.25
    POSITIVE LOGITS
     celebrate
    1.11
    celebrate
    0.99
     celebrating
    0.93
     celebrates
    0.90
    celebr
    0.88
     Celebrate
    0.85
     celebration
    0.84
     honour
    0.81
    Celebrate
    0.81
    elebr
    0.80
    Activations Density 0.013%

    No Known Activations