© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15976
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related expressions indicating ownership

    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
     techn
    -0.52
     deren
    -0.51
     نکنید
    -0.47
     dessen
    -0.45
     encephal
    -0.44
    tshell
    -0.43
    MethodManager
    -0.41
    nelle
    -0.41
    Derbyniad
    -0.40
    actual
    -0.40
    POSITIVE LOGITS
     sua
    1.75
     seu
    1.60
     seus
    1.41
     suas
    1.32
     suo
    1.20
     svoje
    1.20
     своей
    1.17
     své
    1.13
     swoje
    1.09
     swojej
    1.09
    Activations Density 0.446%

    No Known Activations