© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7061
    Prev
    Next
    INDEX
    Explanations

    references to islands and associated geographical terms

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

    islands

    np_acts-logits-general · gemini-2.0-flash

    island nation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wach
    -0.43
     بخ
    -0.43
     Bec
    -0.40
     Motive
    -0.39
     richt
    -0.39
    ⬅
    -0.38
     Req
    -0.38
     FetchType
    -0.37
     requirement
    -0.37
     FEC
    -0.37
    POSITIVE LOGITS
     island
    2.23
     Island
    2.22
    Island
    2.13
     ISLAND
    2.08
    island
    1.98
     islands
    1.80
     Islands
    1.76
    islands
    1.61
    Islands
    1.61
     ISLANDS
    1.57
    Activations Density 0.077%

    No Known Activations