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. 9114
    Prev
    Next
    INDEX
    Explanations

    references to meteorological advancements and cloud seeding technologies

    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
    WebServlet
    -0.49
    requestCode
    -0.49
     lemp
    -0.48
    <%=
    -0.47
    philis
    -0.46
     Schles
    -0.45
    Π
    -0.45
     π
    -0.45
    Arkansas
    -0.44
    Selen
    -0.44
    POSITIVE LOGITS
     Dubai
    1.47
     UAE
    1.40
    Dubai
    1.30
     emirates
    1.22
     Emirates
    1.21
     Emir
    1.17
     dubai
    1.16
     Sharjah
    1.16
    UAE
    1.13
    Emir
    1.07
    Activations Density 0.083%

    No Known Activations