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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 3385
    Prev
    Next
    INDEX
    Explanations

    references to specific islands and their geographical contexts

    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
     nakalista
    -0.53
    kelijkheid
    -0.49
    dir
    -0.47
     مُعرِّف
    -0.45
     trình
    -0.45
     estekak
    -0.45
     formales
    -0.44
    celotti
    -0.43
    ↵
    -0.42
     strada
    -0.42
    POSITIVE LOGITS
     island
    1.25
     Island
    1.22
     ISLAND
    1.15
    island
    1.14
    Island
    1.14
     islands
    1.09
     Islands
    1.00
    Islands
    0.97
    islands
    0.94
     archipelago
    0.92
    Activations Density 0.307%

    No Known Activations