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. 22-GEMMASCOPE-RES-16K
    6. 12929
    Prev
    Next
    INDEX
    Explanations

    elements related to group actions and movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Beginning a journey or trip

    np_acts-logits-general · gemini-2.0-flash

    embarking or setting out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.72
    TagMode
    -0.71
     onAnimation
    -0.71
    rungsseite
    -0.70
     يتيمه
    -0.69
    =$?
    -0.69
    Билгалдахарш
    -0.68
    Personensuche
    -0.68
    kháu
    -0.68
    ScopeManager
    -0.68
    POSITIVE LOGITS
     embark
    0.97
     set
    0.95
     embarked
    0.95
     departure
    0.93
     departed
    0.92
     depart
    0.90
    出发
    0.90
     travel
    0.90
     travelled
    0.89
     traveled
    0.88
    Activations Density 0.248%

    No Known Activations