© 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. 4-GEMMASCOPE-RES-16K
    11. 11729
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate dependence or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cæsar
    -0.83
    JSONException
    -0.78
     enfance
    -0.73
    dyž
    -0.72
     quoque
    -0.71
    ője
    -0.68
     Sociales
    -0.66
     розта
    -0.65
     bienvenue
    -0.64
     eléctricas
    -0.64
    POSITIVE LOGITS
     without
    2.62
     Without
    2.59
    without
    2.52
    Without
    2.52
     WITHOUT
    2.32
    WITHOUT
    2.23
     ohne
    2.03
    Ohne
    2.00
     senza
    1.91
     zonder
    1.89
    Activations Density 0.093%

    No Known Activations