© 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. 36-GEMMASCOPE-RES-16K
    11. 6753
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "drop" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.66
    Życiorys
    -0.50
    RTDA
    -0.48
     disambiguazione
    -0.48
    culada
    -0.47
    UserScript
    -0.45
     OnInit
    -0.44
    ftagPool
    -0.44
    newBuilder
    -0.44
     propOrder
    -0.44
    POSITIVE LOGITS
     Drop
    1.10
     drop
    1.05
    Drop
    1.02
    drop
    1.00
     DROP
    0.96
     dropped
    0.94
     dropping
    0.88
     Dro
    0.85
    DROP
    0.84
    Dro
    0.84
    Activations Density 0.071%

    No Known Activations