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. 0-GEMMASCOPE-RES-16K
    6. 9824
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to genetic research and its implications in mental health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.51
    oznam
    -0.47
    testens
    -0.47
     bunga
    -0.46
    runApp
    -0.46
    ded
    -0.46
    انجليز
    -0.45
    ngdoc
    -0.44
     bieten
    -0.43
    queryInterface
    -0.43
    POSITIVE LOGITS
    spo
    0.79
     spoiling
    0.78
    RegressionTest
    0.77
     AssemblyCulture
    0.73
     spoil
    0.72
     Spo
    0.70
     resourceCulture
    0.69
    IntoConstraints
    0.68
     spoils
    0.66
    rey
    0.64
    Activations Density 2.686%

    No Known Activations