© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 9745
    Prev
    Next
    INDEX
    Explanations

    negative phrases and concepts that imply negation or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.51
     Zeno
    -0.50
     Sarm
    -0.47
     Ptole
    -0.47
     Philist
    -0.47
     NgModule
    -0.47
    ∬
    -0.46
     Psalms
    -0.43
     Euphrates
    -0.43
     feminina
    -0.43
    POSITIVE LOGITS
     necessarily
    1.08
     necesariamente
    0.95
    necessarily
    0.91
     merely
    0.90
    それとも
    0.87
     just
    0.87
     necessariamente
    0.86
    жели
    0.84
     nécessairement
    0.84
    Jereo
    0.82
    Activations Density 0.201%

    No Known Activations