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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45502
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, specifically islands and archipelagos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    MessageTagHelper
    -0.50
    anyahu
    -0.47
    AccessFile
    -0.47
     oprot
    -0.47
    eradish
    -0.46
    tagHelperRunner
    -0.45
    copg
    -0.45
     الرياضيه
    -0.44
    Slf
    -0.43
     Hollande
    -0.42
    POSITIVE LOGITS
     archipelago
    0.84
     Archipelago
    0.75
     Islands
    0.71
     islands
    0.69
    Islands
    0.57
    ulauan
    0.57
     Isles
    0.53
    islands
    0.52
     ISLANDS
    0.50
    ronesia
    0.49
    Activations Density 0.014%

    No Known Activations