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. 25-GEMMASCOPE-RES-16K
    6. 3589
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and analysis of marine biology, focusing on silicon and sponge systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Thorne
    -0.78
     Chinook
    -0.71
     Thorpe
    -0.68
     Eddie
    -0.65
    edin
    -0.64
     Edd
    -0.61
    Eddie
    -0.59
    Datuak
    -0.59
     Erika
    -0.58
    Thor
    -0.58
    POSITIVE LOGITS
     MP
    1.02
    MP
    0.94
     mp
    0.90
    Mp
    0.87
     Mp
    0.86
     Elizabeth
    0.85
    mp
    0.83
     Zhang
    0.83
    Elizabeth
    0.78
     MPs
    0.77
    Activations Density 1.762%

    No Known Activations