© 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. 9895
    Prev
    Next
    INDEX
    Explanations

    the definite article "The" and variations of it in different contexts

    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
     yapa
    -0.32
     every
    -0.29
     altında
    -0.29
     reír
    -0.28
     yardımcı
    -0.28
     sabes
    -0.28
     nigdy
    -0.27
     in
    -0.27
     einiger
    -0.26
    all
    -0.26
    POSITIVE LOGITS
     ſche
    1.24
    ſelf
    1.20
     ſta
    1.17
     purpoſe
    1.15
     houſe
    1.15
     ddelwed
    1.13
    ſelves
    1.13
    ロウィン
    1.09
     ſeine
    1.09
     ſind
    1.09
    Activations Density 1.993%

    No Known Activations