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. 18-GEMMASCOPE-RES-16K
    6. 10458
    Prev
    Next
    INDEX
    Explanations

    information related to telecommunications and networking market analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    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
    -0.56
     enriquec
    -0.50
     Zayed
    -0.45
    getMinutes
    -0.44
    DotNetBar
    -0.44
     agrade
    -0.44
     sterili
    -0.43
     untersch
    -0.43
    Compat
    -0.43
    馃
    -0.43
    POSITIVE LOGITS
     research
    1.09
     analyst
    1.08
     analysts
    1.06
    research
    0.96
     report
    0.96
     analysis
    0.92
    Analyst
    0.90
     Research
    0.90
     study
    0.90
     Analyst
    0.89
    Activations Density 0.126%

    No Known Activations