© 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. 23-GEMMASCOPE-RES-16K
    11. 11639
    Prev
    Next
    INDEX
    Explanations

    important design concepts and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.84
     виправивши
    -0.64
    IntoConstraints
    -0.60
    twimg
    -0.56
    PerformLayout
    -0.54
    
    -0.49
    TintMode
    -0.49
    Спољашње
    -0.49
    bkz
    -0.48
     HttpNotFound
    -0.48
    POSITIVE LOGITS
     time
    4.41
    time
    3.42
    Time
    3.14
     Time
    3.14
     TIME
    3.05
    TIME
    2.73
     tijd
    2.55
    时间
    2.50
     tiempo
    2.44
     времени
    2.35
    Activations Density 1.741%

    No Known Activations