© 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. 22-GEMMASCOPE-RES-16K
    11. 5597
    Prev
    Next
    INDEX
    Explanations

    sections related to authorship and contributions in academic writing

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

    Korean names or Korean-related words

    np_acts-logits-general · gemini-2.0-flash

    Korean names and Korea

    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
    脚注の使い方
    -0.78
    ]")]
    -0.69
    Tikang
    -0.66
    })->
    -0.66
     Rasp
    -0.63
     lenker
    -0.63
    PMailer
    -0.58
     Volu
    -0.56
     Adirond
    -0.54
    CppMethod
    -0.54
    POSITIVE LOGITS
     Korean
    1.82
     Korea
    1.75
    Korean
    1.61
     Seoul
    1.60
    Korea
    1.56
     Koreans
    1.49
     korean
    1.45
    Seoul
    1.39
     korea
    1.37
    korean
    1.24
    Activations Density 0.303%

    No Known Activations