Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15691
    Prev
    Next
    INDEX
    Explanations

    the word "your" and its variations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -1.08
     Normdatei
    -1.04
    Personensuche
    -1.03
     himself
    -1.02
    DockStyle
    -0.96
     Himself
    -0.95
    himself
    -0.93
    awtextra
    -0.87
    IndentedString
    -0.79
    AddAttribute
    -0.79
    POSITIVE LOGITS
     your
    1.47
    your
    1.30
     Your
    1.21
    YOUR
    1.21
     YOUR
    1.20
    Your
    1.16
     our
    1.13
     votre
    1.12
     own
    1.09
     vostro
    1.05
    Activations Density 0.075%

    No Known Activations