© 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. 7-GEMMASCOPE-RES-16K
    11. 6793
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Racine
    -0.93
     uſe
    -0.86
     cauſe
    -0.83
     purpoſe
    -0.79
     pleaſure
    -0.79
    cys
    -0.77
     ſuch
    -0.77
     leaſt
    -0.75
     Conci
    -0.74
     stiefel
    -0.74
    POSITIVE LOGITS
     him
    1.36
     them
    1.29
     Him
    1.28
    Him
    1.26
     Them
    1.25
     HIM
    1.24
     THEM
    1.20
    them
    1.14
     herself
    1.13
    Them
    1.13
    Activations Density 0.121%

    No Known Activations