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. 14277
    Prev
    Next
    INDEX
    Explanations

    references to Facebook and its features, particularly around its design and social media functions

    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
    SBATCH
    -0.52
     uintptr
    -0.51
     BoxFit
    -0.47
    AntiForgeryToken
    -0.46
    anggil
    -0.46
    цездатний
    -0.44
    TestFixture
    -0.44
     dumne
    -0.44
     cref
    -0.44
    fertigung
    -0.42
    POSITIVE LOGITS
     platform
    1.26
     users
    1.22
     platforms
    1.10
    platform
    1.07
     user
    1.05
     Platforms
    1.05
     Platform
    1.02
     Users
    1.01
     plataforma
    0.94
     Plattform
    0.90
    Activations Density 0.592%

    No Known Activations