© 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 EvalsExportsAPI 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. 96583
    Prev
    Next
    INDEX
    Explanations

    terms related to baked goods, particularly muffins and cupcakes

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

    muffin, cupcake, coffin, paraffin

    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
    RSpec
    -0.50
     Nara
    -0.48
     kasarigan
    -0.48
    QMetaType
    -0.44
     States
    -0.43
     Rath
    -0.42
     země
    -0.40
     Warne
    -0.40
    Firestore
    -0.40
    TintMode
    -0.40
    POSITIVE LOGITS
     muffin
    2.14
     muffins
    2.02
     Muffins
    1.77
    muffin
    1.74
    Muffin
    1.56
     cupcake
    1.07
    Muff
    1.06
     cupcakes
    1.00
     Cupcake
    0.93
    ffin
    0.93
    Activations Density 0.004%

    No Known Activations