© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4532
    Prev
    Next
    INDEX
    Explanations

    the word "that" and related relative pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skrevet
    -0.62
     käns
    -0.60
     sqlSession
    -0.58
     nák
    -0.57
     snowing
    -0.55
    Nef
    -0.53
    uous
    -0.52
     desorption
    -0.52
     alimentaires
    -0.52
     nationaux
    -0.52
    POSITIVE LOGITS
     could
    0.95
     have
    0.89
     had
    0.88
     would
    0.87
     can
    0.84
     has
    0.84
     consistently
    0.83
     οποίο
    0.81
    >`;
    0.81
     typically
    0.80
    Activations Density 0.373%

    No Known Activations