© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2209
    Prev
    Next
    INDEX
    Explanations

    instances of the word "switch" and its variations, indicating shifts in focus or opinion

    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
    msleep
    -0.35
     pember
    -0.35
     Gründ
    -0.33
    richTextPanel
    -0.29
     تضيفلها
    -0.29
    NameInMap
    -0.29
    Datuak
    -0.29
    }());
    -0.28
    Rüyada
    -0.28
     Truth
    -0.28
    POSITIVE LOGITS
     gears
    1.02
     hemispheres
    0.91
     sexes
    0.72
     genres
    0.71
     continents
    0.70
    gears
    0.70
     gear
    0.68
     genders
    0.68
     sides
    0.68
     lanes
    0.68
    Activations Density 0.234%

    No Known Activations