© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15388
    Prev
    Next
    INDEX
    Explanations

    characters and names related to the "GA" (possibly geographical area or a category) in various contexts

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

    "Ga" followed by specific characters

    np_acts-logits-general · gemini-2.0-flash

    GA Research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ीय
    -0.57
     comp
    -0.49
    vale
    -0.48
    tolu
    -0.47
     compter
    -0.47
    yq
    -0.47
    isuus
    -0.47
    قل
    -0.47
    щу
    -0.47
    endroit
    -0.47
    POSITIVE LOGITS
    webElementXpaths
    1.12
    MigrationBuilder
    0.98
    DockStyle
    0.88
    contentLoaded
    0.84
     onAnimation
    0.83
     تضيفلها
    0.81
    ThroughAttribute
    0.76
    httphttps
    0.73
     دیکھیے
    0.71
    (!__
    0.70
    Activations Density 0.101%

    No Known Activations