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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4525
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and their characteristics, particularly islands and their attributes

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

    Island or islands

    np_acts-logits-general · gemini-2.0-flash

    places and archipelagos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.62
     lenker
    -0.60
    afficheront
    -0.57
     '\\;'
    -0.55
     canadensis
    -0.55
    MLLoader
    -0.55
    tanleria
    -0.55
    bootstrapcdn
    -0.54
    énario
    -0.54
    lamabad
    -0.54
    POSITIVE LOGITS
     island
    1.72
     islands
    1.63
     Island
    1.46
     Islands
    1.43
    island
    1.39
    Island
    1.33
     ISLAND
    1.31
     islanders
    1.31
     archipelago
    1.29
    islands
    1.24
    Activations Density 0.161%

    No Known Activations