© 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. 11298
    Prev
    Next
    INDEX
    Explanations

    conjunctions that indicate contrast or exceptions

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

    Comes before a comma

    np_acts-logits-general · gemini-2.0-flash

    however,

    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
    '},
    -0.84
     purpoſe
    -0.80
     Italijanski
    -0.78
    '):
    -0.78
    "):
    -0.77
    '};
    -0.77
    NUMX
    -0.76
    AndEndTag
    -0.76
    SequentialGroup
    -0.76
    '],$
    -0.75
    POSITIVE LOGITS
    ,
    0.51
    diğinde
    0.48
    catchError
    0.48
    TestFixture
    0.45
     quite
    0.45
    
    0.45
    tki
    0.43
    googleapis
    0.43
    diğ
    0.43
    лан
    0.43
    Activations Density 0.114%

    No Known Activations