© 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. 3585
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to bias and political discourse

    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
     muß
    -1.10
     läßt
    -1.09
     idéia
    -1.05
     متعلقه
    -1.02
     müßte
    -0.96
     mußte
    -0.94
     daß
    -0.92
     Moslem
    -0.91
     mußten
    -0.91
     especiais
    -0.87
    POSITIVE LOGITS
     impactful
    1.05
     microbiome
    1.04
     curated
    0.99
     leveraging
    0.98
     timelines
    0.98
    TLDR
    0.98
     incentiv
    0.96
     nuanced
    0.96
     sourced
    0.95
     overarching
    0.95
    Activations Density 6.160%

    No Known Activations