© 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. 15-GEMMASCOPE-RES-16K
    11. 11861
    Prev
    Next
    INDEX
    Explanations

    concepts related to trust and confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nge
    -0.56
    quel
    -0.55
    шое
    -0.54
     mot
    -0.52
    jspb
    -0.51
    èche
    -0.50
    orno
    -0.49
    lage
    -0.49
     vies
    -0.49
     ITIS
    -0.49
    POSITIVE LOGITS
     trusting
    1.19
     fiducia
    1.17
     confiance
    1.12
     trusted
    1.09
     trust
    1.08
     confiar
    1.03
    trust
    1.01
    trusted
    1.01
     trustworthy
    1.00
     trusts
    0.98
    Activations Density 0.181%

    No Known Activations