© 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. 15404
    Prev
    Next
    INDEX
    Explanations

    the act of thinking or prompts to reflect critically

    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
     nahilalakip
    -0.94
    UpInside
    -0.86
     Audiodateien
    -0.85
     تضيفلها
    -0.84
     Garvey
    -0.83
     Bradbury
    -0.80
     BorderRadius
    -0.80
     medesimo
    -0.79
     effusion
    -0.79
    DialogContent
    -0.78
    POSITIVE LOGITS
    Think
    2.09
    THINK
    2.08
     THINK
    2.08
     Think
    2.07
     think
    2.03
    think
    1.97
     thinks
    1.81
     thinking
    1.64
     Thinking
    1.63
    Thinking
    1.57
    Activations Density 0.117%

    No Known Activations