© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15480
    Prev
    Next
    INDEX
    Explanations

    elements related to legal proceedings and documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.71
    ViewFeatures
    -0.64
     שוליים
    -0.59
    ValueStyle
    -0.54
     autorytatywna
    -0.50
    queryInterface
    -0.50
    //</
    -0.49
    tagHelperRunner
    -0.49
     DbSet
    -0.47
     برانيه
    -0.47
    POSITIVE LOGITS
     ensuring
    0.60
     чтобы
    0.58
     ensures
    0.54
     assuring
    0.52
     upang
    0.52
     ensure
    0.48
     seeking
    0.47
    เพื่อ
    0.46
     offering
    0.46
     affinch
    0.46
    Activations Density 0.823%

    No Known Activations