© 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. 0-GEMMASCOPE-RES-16K
    11. 7135
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "OK" or its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.94
     neceff
    -0.91
     reaſon
    -0.90
     ſtate
    -0.87
     myſelf
    -0.86
     juſ
    -0.85
     poffible
    -0.85
     Monfieur
    -0.83
     pleaſure
    -0.83
     fubject
    -0.82
    POSITIVE LOGITS
     shorter
    1.05
     smaller
    1.01
     lesser
    0.81
    smaller
    0.72
     Smaller
    0.70
     lower
    0.66
     bag
    0.65
    Smaller
    0.64
     pat
    0.61
     Shorter
    0.58
    Activations Density 0.149%

    No Known Activations