© 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 - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 5136
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hard" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.84
     propOrder
    -0.82
    AccessorTable
    -0.80
     MonoBehaviour
    -0.77
     تضيفلها
    -0.77
    IndentedString
    -0.73
    abestanden
    -0.72
     InputDecoration
    -0.72
     ویکی‌پدیا
    -0.71
     ostavi
    -0.70
    POSITIVE LOGITS
     hard
    1.38
     Hard
    1.31
     HARD
    1.26
    HARD
    1.20
    Hard
    1.20
    hard
    1.15
     harder
    0.98
    硬
    0.91
     hardest
    0.87
     harde
    0.87
    Activations Density 0.044%

    No Known Activations