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. 20-GEMMASCOPE-RES-16K
    6. 13038
    Prev
    Next
    INDEX
    Explanations

    terms related to political and economic systems, particularly focusing on leadership and citizenship issues

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

    Prepositions

    np_acts-logits-general · gemini-2.0-flash

    both ... and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '
    -0.43
     /
    -0.42
     outro
    -0.41
    くらい
    -0.41
     lắm
    -0.40
     çık
    -0.40
    くらいで
    -0.39
     outros
    -0.39
     другому
    -0.39
    ودی
    -0.39
    POSITIVE LOGITS
    \{\\
    0.93
    owohl
    0.89
     Efq
    0.84
    windowFixed
    0.83
     både
    0.82
     zarówno
    0.81
     myſelf
    0.79
     sowohl
    0.79
     zowel
    0.79
    +#+
    0.78
    Activations Density 0.652%

    No Known Activations