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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12618
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and finance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aDecoder
    -0.55
     AssemblyTitle
    -0.55
     http
    -0.54
     idéia
    -0.50
    istoitu
    -0.49
    http
    -0.47
    MemoryWarning
    -0.42
    BeginContext
    -0.41
     Obama
    -0.41
    SaveSave
    -0.40
    POSITIVE LOGITS
     metaverse
    0.99
     covid
    0.99
     TikTok
    0.96
    Covid
    0.96
     Covid
    0.94
     COVID
    0.93
    COVID
    0.92
     Metaverse
    0.91
    covid
    0.88
    pandemic
    0.88
    Activations Density 1.547%

    No Known Activations