© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4498
    Prev
    Next
    INDEX
    Explanations

    instances of the word "leave" and its variations, indicating a focus on the concept of departing or escaping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ronique
    -0.47
    infix
    -0.47
    RTLR
    -0.47
    reth
    -0.45
    kháu
    -0.45
     Magen
    -0.44
    osi
    -0.42
    IAM
    -0.42
    setOption
    -0.41
     Paglinawan
    -0.41
    POSITIVE LOGITS
    AndEndTag
    0.81
     departure
    0.70
     поки
    0.68
     quitte
    0.65
     smtplib
    0.64
     quitté
    0.64
    enderror
    0.64
     meninggalkan
    0.63
     Departure
    0.61
     leave
    0.60
    Activations Density 0.159%

    No Known Activations