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. 5-GEMMASCOPE-RES-16K
    6. 4849
    Prev
    Next
    INDEX
    Explanations

    content related to screenplays and screenplay writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hozzáférés
    -0.61
    interopRequire
    -0.59
    ?}",
    -0.54
    теризу
    -0.52
    assertArray
    -0.51
    évaluateur
    -0.50
     AssemblyCompany
    -0.50
    getCollection
    -0.50
     HAC
    -0.49
    dostęp
    -0.49
    POSITIVE LOGITS
     screenplay
    0.98
    Scénario
    0.95
     scripts
    0.83
     script
    0.83
     screenwriter
    0.80
    脚本
    0.74
     lyrics
    0.72
    ricist
    0.72
     playwright
    0.70
    énario
    0.70
    Activations Density 0.423%

    No Known Activations