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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6026
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and syntax relevant to mathematical expressions and operations

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

    "math" or "Math" and related terms

    np_acts-logits-general · gemini-2.0-flash

    mathematics and math utilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.11
     becauſe
    -1.06
     Jefus
    -1.04
     poffe
    -0.99
     themſelves
    -0.98
     initComponents
    -0.97
     cauſe
    -0.97
     againſt
    -0.93
     himſelf
    -0.92
     consultato
    -0.92
    POSITIVE LOGITS
     Mathis
    1.07
     Math
    1.00
     math
    0.93
     MATH
    0.89
    Math
    0.80
    math
    0.80
    MATH
    0.75
     mathematics
    0.65
     equations
    0.62
    matical
    0.62
    Activations Density 0.169%

    No Known Activations