© 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. 30-GEMMASCOPE-RES-16K
    6. 10628
    Prev
    Next
    INDEX
    Explanations

    references to academic and research institutions along with their locations

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

    Location after a comma or preposition

    np_acts-logits-general · gemini-2.0-flash

    company locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     institutions
    -0.43
    badlogic
    -0.41
     churches
    -0.37
     cancers
    -0.36
     Hackney
    -0.36
     pharmacies
    -0.35
     Truy
    -0.35
    
    -0.35
     boutiques
    -0.35
     hospitals
    -0.35
    POSITIVE LOGITS
    ThemeOverlay
    0.59
    ViewFeatures
    0.59
    总部
    0.57
     Numerade
    0.55
     ویکی‌پدی
    0.52
    EDEFAULT
    0.51
     للاسماء
    0.51
    addCriterion
    0.51
    matchCondition
    0.49
    jspb
    0.49
    Activations Density 0.302%

    No Known Activations