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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 7365
    Prev
    Next
    INDEX
    Explanations

    the word "Your" and variations highlighting possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.73
     ویکی‌پدیا
    -0.54
    ecore
    -0.53
    DockStyle
    -0.53
     Fudge
    -0.53
     chắn
    -0.51
     =
    -0.51
     knobs
    -0.50
     textStatus
    -0.50
    ;
    -0.49
    POSITIVE LOGITS
     your
    1.19
    YOUR
    1.16
    your
    1.14
     YOUR
    1.03
     votre
    1.03
    ]))
    
    1.02
     *)__
    1.01
    intellij
    1.00
    votre
    1.00
     vuestro
    0.99
    Activations Density 0.074%

    No Known Activations