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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7881
    Prev
    Next
    INDEX
    Explanations

    terms related to advanced mathematical concepts and transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.46
    ViewFeatures
    -0.40
     propOrder
    -0.39
     cherchés
    -0.36
     предпо
    -0.36
     fourrure
    -0.35
     stră
    -0.34
    AndEndTag
    -0.34
     विश्वसनीयता
    -0.31
    ITHER
    -0.31
    POSITIVE LOGITS
     surla
    0.51
    的概念
    0.50
     vs
    0.50
     BoxFit
    0.49
    什么是
    0.49
    ParseTree
    0.48
    所謂
    0.47
     typ
    0.47
     concept
    0.46
     BaseEntity
    0.46
    Activations Density 1.088%

    No Known Activations