© 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. 83103
    Prev
    Next
    INDEX
    Explanations

    references to the word "mas" in various contexts, particularly related to celebrations or festivals

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

    Candlemas, Lammas, loaf mass

    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
     jep
    -0.42
    lekt
    -0.41
     Ilustra
    -0.40
    AndEndTag
    -0.40
    ılacak
    -0.39
    quelle
    -0.39
    তথ্যসূত্র
    -0.39
     gynnwys
    -0.38
     antidesliz
    -0.38
    发表于
    -0.38
    POSITIVE LOGITS
    mas
    3.11
     mas
    2.78
    MAS
    2.52
     Mas
    2.44
    Mas
    2.42
     MAS
    2.27
    masa
    1.53
    amas
    1.42
    MASS
    1.40
    omas
    1.38
    Activations Density 0.019%

    No Known Activations