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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 11549
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "speaking" or variations of the word "mine" such as "my"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -1.07
    textTheme
    -0.91
     المعيارى
    -0.88
    RectangleBorder
    -0.85
     Bress
    -0.84
     HasFactory
    -0.84
    ThroughAttribute
    -0.83
     للمعارف
    -0.81
    Datuak
    -0.77
    новниш
    -0.77
    POSITIVE LOGITS
    I
    0.62
    T
    0.58
    Speaking
    0.58
     på
    0.57
    so
    0.55
    berapa
    0.55
     naar
    0.53
     astfel
    0.51
    To
    0.50
    Hi
    0.49
    Activations Density 0.030%

    No Known Activations