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. 10-GEMMASCOPE-RES-16K
    6. 11726
    Prev
    Next
    INDEX
    Explanations

    the use of the word "particular" in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BufferedImage
    -0.81
    hands
    -0.79
    dozer
    -0.78
     useEffect
    -0.77
     Doris
    -0.72
    miary
    -0.72
    vidas
    -0.70
     ItemStack
    -0.70
    IsContent
    -0.69
    
    -0.69
    POSITIVE LOGITS
     particulares
    0.88
     particular
    0.87
    ticularly
    0.84
     Particular
    0.78
    particular
    0.77
    Particular
    0.74
     PARTICULAR
    0.74
     partic
    0.73
     speci
    0.72
     McGu
    0.69
    Activations Density 0.069%

    No Known Activations