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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8555
    Prev
    Next
    INDEX
    Explanations

    the word "your" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.47
     deriv
    -0.38
    DrawerToggle
    -0.37
    Deriv
    -0.37
    didReceive
    -0.35
     وصلة
    -0.35
     Deriv
    -0.35
    Derived
    -0.35
    Scha
    -0.34
     imagin
    -0.34
    POSITIVE LOGITS
     your
    1.59
    your
    1.20
     votre
    1.00
     jūsų
    0.96
    ของคุณ
    0.93
    votre
    0.88
     Ihrer
    0.85
     vaše
    0.85
     вашего
    0.85
     вашу
    0.85
    Activations Density 0.084%

    No Known Activations