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. 20-GEMMASCOPE-RES-16K
    6. 12385
    Prev
    Next
    INDEX
    Explanations

    technical language related to solving mathematical equations, particularly differential and functional equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.59
     consultato
    -0.56
    willReturn
    -0.53
     مرئيه
    -0.53
    ochet
    -0.51
     NUKAT
    -0.49
     Wicidata
    -0.48
    BSITE
    -0.48
    蒙
    -0.47
    ۜ
    -0.46
    POSITIVE LOGITS
     equations
    1.53
     equation
    1.47
     Equations
    1.21
    equations
    1.18
    equation
    1.10
     Equation
    1.08
    Equations
    1.08
     équ
    1.02
    Equation
    1.00
    quations
    0.99
    Activations Density 0.915%

    No Known Activations