Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-GEMMASCOPE-RES-16K
    6. 9586
    Prev
    Next
    INDEX
    Explanations

    instances of the word "brief."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setContentView
    -0.61
     Ellison
    -0.59
    Xaml
    -0.50
    的说道
    -0.50
     haunted
    -0.49
     năng
    -0.48
    的问道
    -0.48
    production
    -0.48
    ַת
    -0.47
    podar
    -0.46
    POSITIVE LOGITS
     brief
    4.58
     Brief
    4.21
    Brief
    3.99
    brief
    3.94
     BRIEF
    3.66
    BRIEF
    3.14
     briefly
    3.08
     briefs
    2.95
     Briefs
    2.64
     Briefly
    2.56
    Activations Density 0.091%

    No Known Activations