© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15859
    Prev
    Next
    INDEX
    Explanations

    the word "unlike" and its variations to signal contrasts or differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     muſt
    -0.70
     becauſe
    -0.61
     papy
    -0.57
     subgoal
    -0.56
    zbęd
    -0.56
     урна
    -0.56
     presumption
    -0.55
     Annette
    -0.55
    corder
    -0.54
     alſo
    -0.53
    POSITIVE LOGITS
     unlike
    1.84
    unlike
    1.81
     Unlike
    1.69
    Unlike
    1.68
    Contrary
    0.91
     Gegensatz
    0.89
     отличие
    0.89
     Like
    0.82
     diferencia
    0.81
     Contrary
    0.81
    Activations Density 0.096%

    No Known Activations