© 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-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 11463
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to claims of rights violations and grievances in a judicial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.84
    oredCriteria
    -0.64
    IntoConstraints
    -0.59
    Демографія
    -0.55
     Normdatei
    -0.54
    InputTagHelper
    -0.53
    RegistryLite
    -0.52
    ագրություններ
    -0.51
     AssemblyCulture
    -0.50
    UrlResolution
    -0.50
    POSITIVE LOGITS
     injustice
    0.96
     injustices
    0.94
     unfair
    0.83
     injust
    0.76
     unjust
    0.76
     oppression
    0.73
     injus
    0.73
     wrongs
    0.68
     unjustly
    0.67
     abuse
    0.65
    Activations Density 0.970%

    No Known Activations