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. 22-GEMMASCOPE-RES-16K
    6. 5726
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to politics and governance

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

    "United States" or country names

    np_acts-logits-general · gemini-2.0-flash

    United States government

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.63
     esetén
    -0.63
    ريكا
    -0.63
     &___
    -0.59
    Präsident
    -0.56
    /**
    -0.54
    ként
    -0.54
     transfieras
    -0.53
    atism
    -0.53
    AndEndTag
    -0.50
    POSITIVE LOGITS
     electorate
    0.80
     economy
    0.77
     fanbase
    0.74
     rhestr
    0.74
     legislature
    0.72
     hierarchy
    0.71
     judiciary
    0.71
     populace
    0.69
    osphere
    0.69
     workforce
    0.69
    Activations Density 0.495%

    No Known Activations