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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8782
    Prev
    Next
    INDEX
    Explanations

    words related to roles and responsibilities in legal contexts

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

    preceding professions or roles

    np_acts-logits-general · gemini-2.0-flash

    legal report or reporting

    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
     resourceCulture
    -0.48
     Paying
    -0.44
    Paying
    -0.43
     paying
    -0.41
     membayar
    -0.41
     Meksiku
    -0.41
    blico
    -0.40
    OGND
    -0.39
    ケティング
    -0.39
    oyant
    -0.38
    POSITIVE LOGITS
     report
    0.62
    report
    0.54
     working
    0.54
     reports
    0.52
     reporting
    0.51
    reports
    0.49
     Report
    0.47
     role
    0.47
    Report
    0.47
    tugas
    0.46
    Activations Density 0.779%

    No Known Activations