© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 2774
    Prev
    Next
    INDEX
    Explanations

    causal or conditional statements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hochspringen
    -0.67
    RegressionTest
    -0.65
    NewLabel
    -0.64
     myſelf
    -0.64
    ſelves
    -0.63
     ſeveral
    -0.62
    zczy
    -0.60
     Hotspur
    -0.60
     Theſe
    -0.58
     الدولى
    -0.57
    POSITIVE LOGITS
     because
    0.80
    畢竟
    0.80
     Ведь
    0.79
    毕竟
    0.78
    Cuz
    0.76
     Because
    0.75
     Sebab
    0.74
    cuz
    0.72
    because
    0.72
    Because
    0.72
    Activations Density 0.290%

    No Known Activations