© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11347
    Prev
    Next
    INDEX
    Explanations

    references to the Middle East and related dietary concerns

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

    "Middle East"

    np_acts-logits-general · gemini-2.0-flash

    Middle East

    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
     an
    -0.49
    8
    -0.49
     An
    -0.42
     Eighty
    -0.42
    VersionUID
    -0.41
    ,
    -0.40
     und
    -0.39
     eight
    -0.39
     ar
    -0.38
    ar
    -0.38
    POSITIVE LOGITS
     '\\;'
    0.87
     propOrder
    0.83
    PyExc
    0.83
    脚注の使い方
    0.81
    出版年
    0.80
    IsContent
    0.79
     صوتيه
    0.79
    
    0.74
    ValueStyle
    0.73
     pinulongan
    0.72
    Activations Density 0.702%

    No Known Activations