© 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. 14-GEMMASCOPE-RES-16K
    11. 5104
    Prev
    Next
    INDEX
    Explanations

    elements related to academic propositions and research objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.49
     perd
    -0.48
    els
    -0.46
    sä
    -0.44
    কার
    -0.44
     op
    -0.44
     Er
    -0.43
     “
    -0.43
     e
    -0.42
    </b>
    -0.42
    POSITIVE LOGITS
     therefore
    0.94
    そんな
    0.79
    はその
    0.77
    そのような
    0.77
    therefore
    0.76
     therefor
    0.76
     entanto
    0.76
     därför
    0.75
     accordingly
    0.73
     however
    0.73
    Activations Density 1.063%

    No Known Activations