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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28866
    Prev
    Next
    INDEX
    Explanations

    the word "rather" in varying contexts

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

    but rather

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Демографія
    -0.84
     Мексичка
    -0.81
    '},
    
    -0.77
     ―――――
    -0.72
     وتسجيلات
    -0.71
     myſelf
    -0.69
    );\
    -0.69
     GIPHY
    -0.69
     المعيارى
    -0.69
    nachron
    -0.68
    POSITIVE LOGITS
     it
    0.79
     there
    0.73
     we
    0.69
     they
    0.66
    ,
    0.63
     the
    0.58
    ”
    0.54
    DockStyle
    0.53
     you
    0.53
     I
    0.52
    Activations Density 0.169%

    No Known Activations