© 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. 10-GEMMASCOPE-RES-16K
    11. 10281
    Prev
    Next
    INDEX
    Explanations

    references to previous actions, conditions, or entities within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.92
    featureID
    -0.90
     мәкал
    -0.88
     cherchés
    -0.83
     للمعارف
    -0.81
    Enllaces
    -0.79
    SequentialGroup
    -0.78
     ProtoMessage
    -0.78
    __(/*!
    -0.77
    ///</
    -0.76
    POSITIVE LOGITS
     existing
    0.91
     already
    0.77
     previous
    0.74
     Existing
    0.72
    existing
    0.71
    Existing
    0.66
     EXISTING
    0.65
     bestehenden
    0.65
     bestaande
    0.64
     existentes
    0.64
    Activations Density 0.612%

    No Known Activations