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. 8-GEMMASCOPE-RES-16K
    6. 15041
    Prev
    Next
    INDEX
    Explanations

    introductory phrases that set context for a discussion or argument

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )";
    
    -0.95
     iconFacebook
    -0.87
    $.
    
    -0.86
     contextLoads
    -0.86
     myſelf
    -0.85
    Datuak
    -0.83
    hæng
    -0.83
    bereits
    -0.83
     웹툰
    -0.82
    InjectAttribute
    -0.80
    POSITIVE LOGITS
     somebody
    0.88
     everybody
    0.86
     really
    0.78
     stuff
    0.77
    Everybody
    0.75
     people
    0.71
    Somebody
    0.71
     Everybody
    0.69
     Somebody
    0.68
     big
    0.66
    Activations Density 1.373%

    No Known Activations