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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14366
    Prev
    Next
    INDEX
    Explanations

    names or titles related to individuals, particularly with a focus on the prefix "van der."

    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
     itſelf
    -1.35
     myſelf
    -1.19
     Efq
    -1.05
     themſelves
    -1.03
     poffible
    -1.02
     Majefty
    -1.01
     purpoſe
    -0.95
     ſeveral
    -0.95
     pleaſure
    -0.95
     iſt
    -0.95
    POSITIVE LOGITS
     Van
    0.96
     van
    0.89
    Van
    0.80
     Vanden
    0.74
     vans
    0.72
     Vander
    0.70
     VAN
    0.68
     Mc
    0.67
    :✨
    0.65
     von
    0.64
    Activations Density 0.166%

    No Known Activations