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. 6124
    Prev
    Next
    INDEX
    Explanations

    the term "destination" in various contexts

    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
    Биография
    -0.72
    webElementXpaths
    -0.70
     دیکھیے
    -0.68
     оригіналу
    -0.62
    ,:),
    -0.62
     "..\..\..\
    -0.62
     Balan
    -0.61
     unknownFields
    -0.59
    numerusform
    -0.59
    WithIOException
    -0.58
    POSITIVE LOGITS
     destination
    1.01
     ministry
    0.91
    destination
    0.88
     Ministry
    0.82
    Dest
    0.81
    Destination
    0.80
     colspan
    0.80
     ministries
    0.78
     Destination
    0.77
     dest
    0.75
    Activations Density 0.063%

    No Known Activations