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

    Neuronpedia

    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. 78359
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions particularly involving remainders and common denominators

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

    mathematical equations

    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
     OMITBAD
    -1.00
    AndEndTag
    -0.93
     للمعارف
    -0.91
    IndentedString
    -0.91
     dAtA
    -0.91
    IntoConstraints
    -0.91
    +#+#
    -0.90
    Хьажоргаш
    -0.90
    ьаж
    -0.90
     disambiguazione
    -0.86
    POSITIVE LOGITS
    <eos>
    0.32
     "
    0.28
     
    0.25
     &
    0.24
    ...
    0.24
     ne
    0.23
     legal
    0.23
     est
    0.23
    ↵↵
    0.22
    ,
    0.22
    Activations Density 0.626%

    No Known Activations