© 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. 2-GEMMASCOPE-RES-16K
    11. 15412
    Prev
    Next
    INDEX
    Explanations

    the Japanese particle "と" indicating connections or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    思います
    -0.63
    事です
    -0.63
    WriteBarrier
    -0.59
    気がします
    -0.56
    思った
    -0.54
    ことはありません
    -0.50
    のかもしれません
    -0.49
    ことです
    -0.48
    くれない
    -0.48
     angela
    -0.48
    POSITIVE LOGITS
    と
    2.71
     と
    1.75
    りと
    1.47
    와
    1.46
    과
    1.43
    とお
    1.39
    ーと
    1.34
    いと
    1.27
    とも
    1.21
    との
    1.16
    Activations Density 0.028%

    No Known Activations