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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8712
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to verification and assurance in processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     utafitiHapana
    -0.59
    ніципалі
    -0.56
     BitmapFactory
    -0.53
    tanleria
    -0.52
     estekak
    -0.50
     surla
    -0.50
     AssemblyTitle
    -0.49
    __(/*!
    -0.48
    oneofs
    -0.48
    yarnpkg
    -0.48
    POSITIVE LOGITS
    Ensure
    0.60
     ensure
    0.58
     adequate
    0.57
     proper
    0.57
     Ensure
    0.54
     correcta
    0.52
     correcto
    0.51
    ensure
    0.51
     Pastikan
    0.50
     ensuring
    0.49
    Activations Density 0.185%

    No Known Activations