© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12704
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "world" and discussions about its conditions or improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     atle
    -0.55
    BarItem
    -0.51
    nél
    -0.50
    rischen
    -0.49
    vos
    -0.48
    فحة
    -0.47
    oin
    -0.46
     تضيفلها
    -0.46
     nobile
    -0.46
    thorne
    -0.46
    POSITIVE LOGITS
     world
    0.94
     mundo
    0.75
     planet
    0.74
    🌎
    0.73
     세계
    0.73
    world
    0.73
     globe
    0.72
     WORLD
    0.72
     värld
    0.71
    WORLD
    0.69
    Activations Density 0.274%

    No Known Activations