© 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. 16-GEMMASCOPE-RES-65K
    11. 29356
    Prev
    Next
    INDEX
    Explanations

    research-related phrases that indicate the need for further investigation or exploration of topics

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

    future work

    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
    #}
    -0.56
    httphttps
    -0.54
    IActionResult
    -0.54
     väli
    -0.52
    elor
    -0.51
     تعدى
    -0.50
    GOTREF
    -0.50
     Hivatalos
    -0.49
    intellij
    -0.49
     Estaba
    -0.48
    POSITIVE LOGITS
     future
    0.74
     further
    0.73
     next
    0.73
    future
    0.68
     Further
    0.68
    contentLoaded
    0.65
    further
    0.65
    featureID
    0.64
    Further
    0.63
     tartalomajánló
    0.62
    Activations Density 0.371%

    No Known Activations