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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 10553
    Prev
    Next
    INDEX
    Explanations

    concepts related to trust and abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.50
     butt
    -0.49
    IVENESS
    -0.47
     celu
    -0.47
    kologi
    -0.47
    ValueStyle
    -0.46
    ulose
    -0.46
    getDoctrine
    -0.45
    ogaster
    -0.44
    Билгалдахарш
    -0.44
    POSITIVE LOGITS
     pourtant
    0.82
     ellers
    0.72
     betrayal
    0.64
     autrefois
    0.61
     inoxidable
    0.61
     inoxid
    0.61
     betrayed
    0.60
     Pourtant
    0.59
     disappointing
    0.57
     trusted
    0.56
    Activations Density 0.240%

    No Known Activations