© 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. 3-GEMMASCOPE-RES-16K
    11. 8102
    Prev
    Next
    INDEX
    Explanations

    themes related to trust and authority in relationships and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ActionListener
    -0.58
     chase
    -0.55
    nanoTime
    -0.51
     chased
    -0.51
    pyplot
    -0.50
    LookAndFeel
    -0.50
     rues
    -0.49
    Feign
    -0.48
     drive
    -0.48
    ObjectMapper
    -0.47
    POSITIVE LOGITS
     trusted
    1.19
    trusted
    1.16
     trusting
    1.09
    Trusted
    1.03
     Vertrauen
    1.01
     trust
    1.00
     confiance
    0.97
     Trusted
    0.96
     vertrouwen
    0.95
     entrusted
    0.92
    Activations Density 0.396%

    No Known Activations