© 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. 10-GEMMASCOPE-RES-16K
    11. 5835
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential actions and the flexibility of decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    crites
    -0.59
    niająca
    -0.54
     sought
    -0.53
    انيف
    -0.52
    pires
    -0.51
     adjudication
    -0.51
    ganj
    -0.50
     >=",
    -0.50
    estrado
    -0.50
    vician
    -0.50
    POSITIVE LOGITS
     fácilmente
    1.14
     facilmente
    1.05
     facilement
    0.99
     easily
    0.98
    easily
    0.91
     can
    0.81
     Easily
    0.80
     safely
    0.79
    也可以
    0.78
    bitField
    0.75
    Activations Density 1.092%

    No Known Activations