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. 16-GEMMASCOPE-RES-16K
    6. 562
    Prev
    Next
    INDEX
    Explanations

    references to social impact and philanthropic initiatives

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

    People or groups creating change

    np_acts-logits-general · gemini-2.0-flash

    youth leadership and activism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Poor
    -0.50
     Poor
    -0.47
    lucene
    -0.46
     kötü
    -0.44
    ("/:
    -0.44
    า
    -0.44
     nicely
    -0.43
    ☠️
    -0.43
    cheduling
    -0.42
    ="",
    -0.42
    POSITIVE LOGITS
    出版年
    0.93
     youth
    0.84
     cataly
    0.81
    preneurship
    0.81
     entrepreneurial
    0.80
     entrepreneurs
    0.77
     leadership
    0.74
     Cataly
    0.72
    youth
    0.71
    Youth
    0.71
    Activations Density 0.142%

    No Known Activations