© 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. 10535
    Prev
    Next
    INDEX
    Explanations

    terms related to legal violations and compliance with regulations

    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
    P
    -0.58
     P
    -0.52
    jackson
    -0.51
    Scar
    -0.49
    J
    -0.48
    ViewBag
    -0.48
    Connections
    -0.47
    ...
    -0.47
    стер
    -0.46
     Grand
    -0.46
    POSITIVE LOGITS
     violations
    1.25
     compliance
    1.18
     Violations
    1.17
     Compliance
    1.16
     comply
    1.10
     adheres
    1.09
    compliance
    1.08
     violation
    1.07
    obey
    1.06
     Violation
    1.06
    Activations Density 0.259%

    No Known Activations