© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6103
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and connections

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

    "and" connecting people

    np_acts-logits-general · gemini-2.0-flash

    and I

    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
     kasarigan
    -0.87
    kháu
    -0.59
     AssemblyProduct
    -0.57
    thâu
    -0.51
    Cyfeiriadau
    -0.50
     Shaksp
    -0.50
     gynhyrchwyd
    -0.48
     Shakspeare
    -0.48
     okuyayım
    -0.48
    Билгалдахарш
    -0.48
    POSITIVE LOGITS
     others
    1.26
    others
    0.94
     his
    0.94
     Others
    0.92
    Others
    0.89
     colleagues
    0.86
     OTHERS
    0.80
     myself
    0.79
     demás
    0.77
     their
    0.75
    Activations Density 0.270%

    No Known Activations