Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1168
    Prev
    Next
    INDEX
    Explanations

    the presence of mathematical symbols and notations, particularly those related to equations and statistical distributions

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

    PAP, cora abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.76
     EconPapers
    -0.70
     Selma
    -0.57
     مرئيه
    -0.57
     שוליים
    -0.56
    
    -0.56
    WaitGroup
    -0.54
     Lyra
    -0.54
    ropractic
    -0.53
    abestanden
    -0.53
    POSITIVE LOGITS
     ModelRenderer
    0.35
    ándolos
    0.34
     Wiktionnaire
    0.32
     surgió
    0.32
     AssemblyVersion
    0.31
     tatuagens
    0.31
     suaminya
    0.31
     Litt
    0.30
     avoient
    0.30
     assin
    0.29
    Activations Density 0.159%

    No Known Activations