© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9955
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to court rulings and motions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Legal rulings or decisions

    np_acts-logits-general · gemini-2.0-flash

    legal rulings and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thâm
    -0.45
     present
    -0.40
     quitting
    -0.40
     prega
    -0.40
     circles
    -0.40
     Qual
    -0.39
    programm
    -0.38
     conventions
    -0.37
     Viel
    -0.37
     pos
    -0.37
    POSITIVE LOGITS
     defaultstate
    0.62
    InputBorder
    0.62
     InputDecoration
    0.57
    IntoConstraints
    0.56
     surla
    0.55
    ChildScrollView
    0.54
    execSQL
    0.54
    gatsby
    0.51
     viewDidLoad
    0.51
     Anordnung
    0.51
    Activations Density 1.418%

    No Known Activations