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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2975
    Prev
    Next
    INDEX
    Explanations

    references to legislative actions and nominations within the Senate

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

    the United States Senate

    np_acts-logits-general · gemini-2.0-flash

    Senate, senators, committees

    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
    __':
    
    -0.72
    ChildScrollView
    -0.59
    ingual
    -0.58
     kasarigan
    -0.58
    rsiniz
    -0.57
     تضيفلها
    -0.55
     Eug
    -0.55
    __":
    
    -0.55
     PLW
    -0.54
    uscitation
    -0.53
    POSITIVE LOGITS
     senators
    1.34
     senator
    1.26
     Senators
    1.23
     Senator
    1.21
     Senate
    1.16
    Senator
    1.08
     SENATE
    0.98
    Senate
    0.98
     senate
    0.97
     senador
    0.94
    Activations Density 0.203%

    No Known Activations