© 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. 15-GEMMASCOPE-RES-16K
    11. 4036
    Prev
    Next
    INDEX
    Explanations

    elements related to legal agreements and moral considerations

    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
     Majefty
    -0.61
     pleaſure
    -0.61
     poffe
    -0.61
     houſe
    -0.58
    ysacchar
    -0.58
    ſelf
    -0.56
     gubern
    -0.56
    iedenis
    -0.56
     متعل
    -0.56
     burs
    -0.55
    POSITIVE LOGITS
    ArrowToggle
    0.59
     quality
    0.55
     compromising
    0.53
     Comprom
    0.51
     compromises
    0.51
     integridad
    0.51
     ویکی‌پدیا
    0.51
    íí
    0.50
     doInBackground
    0.49
     kualitas
    0.49
    Activations Density 0.234%

    No Known Activations