© 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. 28-GEMMASCOPE-RES-16K
    11. 9932
    Prev
    Next
    INDEX
    Explanations

    argumentation and legal terminology, especially related to defense strategies and court rulings

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

    Follows a statement needing further explanation

    np_acts-logits-general · gemini-2.0-flash

    instead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ンド
    -0.29
    бам
    -0.28
    BufferedImage
    -0.27
    ༺
    -0.27
    ]]=
    -0.27
     unions
    -0.27
    getChildAt
    -0.26
     CORON
    -0.26
    familien
    -0.26
     ch
    -0.26
    POSITIVE LOGITS
     instead
    2.80
    Instead
    2.55
     Instead
    2.53
    instead
    2.52
     invece
    1.99
     vielmehr
    1.96
     вместо
    1.88
    tdessen
    1.80
     istället
    1.73
     zamiast
    1.73
    Activations Density 0.849%

    No Known Activations