© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7797
    Prev
    Next
    INDEX
    Explanations

    phrases related to control and autonomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "control" and its translations

    np_acts-logits-general · gemini-2.0-flash

    control, manual, limited

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnimationsModule
    -0.48
    :✨
    -0.38
     nonUne
    -0.35
    xffffffff
    -0.34
    cheiben
    -0.33
    ็จ
    -0.33
     peix
    -0.33
     felic
    -0.32
     disambiguazione
    -0.31
     pép
    -0.31
    POSITIVE LOGITS
     control
    2.64
    control
    2.22
     Control
    2.13
     CONTROL
    2.08
    Control
    1.99
     contrôle
    1.98
     controle
    1.98
     kontrol
    1.95
     controls
    1.93
     Kontrolle
    1.91
    Activations Density 0.590%

    No Known Activations