© 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. 5-GEMMASCOPE-RES-16K
    11. 8760
    Prev
    Next
    INDEX
    Explanations

    terms related to individuals who held prior positions of authority or influence

    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
    HasAnnotation
    -0.86
     sneeze
    -0.86
    IsContent
    -0.81
     Ressources
    -0.80
     fubject
    -0.77
     Marburg
    -0.77
     IndexError
    -0.76
     épis
    -0.75
     springfox
    -0.74
     perſon
    -0.73
    POSITIVE LOGITS
     former
    2.02
     Former
    1.91
    Former
    1.91
    former
    1.68
     ehemalige
    1.49
     ehemaligen
    1.47
     formerly
    1.38
     ehemal
    1.32
     ex
    1.31
     ancien
    1.30
    Activations Density 0.081%

    No Known Activations