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. 8160
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or items, particularly focusing on the context of Lexington, Virginia

    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
     Watson
    -0.69
     ‘
    -0.66
    Watson
    -0.65
    haja
    -0.65
    nun
    -0.63
     Владими
    -0.62
    ある
    -0.61
    Newman
    -0.61
     Sena
    -0.61
     Abs
    -0.61
    POSITIVE LOGITS
     doInBackground
    1.05
     Lexington
    0.96
     MediatR
    0.95
    migrationBuilder
    0.93
    principalColumn
    0.92
    berdayakan
    0.90
    hésite
    0.89
    
    0.89
     ögon
    0.89
     GIP
    0.88
    Activations Density 1.657%

    No Known Activations