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. 5188
    Prev
    Next
    INDEX
    Explanations

    coding or programming-related syntax

    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
    EndTag
    -0.59
    InitVars
    -0.54
     AsyncTask
    -0.52
    argout
    -0.51
    ulsión
    -0.48
    ))))
    -0.48
    modelBuilder
    -0.47
    :✨
    -0.46
    totalPages
    -0.46
    tikzpicture
    -0.46
    POSITIVE LOGITS
     الحره
    0.61
    marginHorizontal
    0.57
     تضيفلها
    0.57
     Tanto
    0.56
    Tanto
    0.56
    ungkinan
    0.56
    ikiki
    0.56
     Wallflower
    0.56
    ciale
    0.55
    IntoConstraints
    0.51
    Activations Density 0.231%

    No Known Activations