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. 12815
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and political processes

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

    Sri Lanka politics

    np_acts-logits-general · gemini-2.0-flash

    Sri Lankan political institutions

    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
    Oklahoma
    -0.76
     Oklahoma
    -0.74
     Bavarian
    -0.63
    ඳ
    -0.62
     Okla
    -0.62
     abstrait
    -0.61
     bayern
    -0.60
     Spanyol
    -0.59
    Seattle
    -0.59
     Romanian
    -0.59
    POSITIVE LOGITS
     Sri
    1.58
     Colombo
    1.33
    Sri
    1.32
     Lanka
    1.27
     Ceylon
    1.21
     Sinh
    1.19
     Lankan
    1.09
     sri
    1.07
     Kandy
    1.01
    sri
    0.93
    Activations Density 0.074%

    No Known Activations