Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 1980
    Prev
    Next
    INDEX
    Explanations

    items related to organizing and storing various types of bags and containers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -1.03
    AndEndTag
    -0.90
    DoubleQuotes
    -0.89
    RegressionTest
    -0.86
    DeleteBehavior
    -0.85
     disponibilités
    -0.85
     disambiguazione
    -0.80
    хьтан
    -0.78
    UrlResolution
    -0.77
    orteur
    -0.77
    POSITIVE LOGITS
     storage
    0.69
     organizer
    0.59
     volume
    0.56
     baga
    0.55
     rangement
    0.54
     drawers
    0.54
     bag
    0.54
     storing
    0.53
     organiz
    0.53
     pouches
    0.51
    Activations Density 0.085%

    No Known Activations