© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11434
    Prev
    Next
    INDEX
    Explanations

    references to control and agency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yawn
    -0.35
    ẵng
    -0.35
     felic
    -0.35
     Процитовано
    -0.34
    っこう
    -0.33
    WireFormatLite
    -0.33
    :✨
    -0.32
    nap
    -0.32
    AsUp
    -0.32
     onAnimation
    -0.31
    POSITIVE LOGITS
     control
    3.06
    control
    2.53
     Control
    2.45
     CONTROL
    2.36
    Control
    2.30
     Kontrolle
    2.28
     contrôle
    2.25
     controle
    2.23
     controllo
    2.17
     controls
    2.16
    Activations Density 0.726%

    No Known Activations