© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 100024
    Prev
    Next
    INDEX
    Explanations

    references to blood and its conditions in various contexts

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

    bloody trails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.65
     initComponents
    -0.65
    FieldBuilder
    -0.60
     సౌకర్య
    -0.57
    AdapterView
    -0.55
    niſſe
    -0.54
     Charms
    -0.53
    InsertCommand
    -0.53
    المناصب
    -0.53
    OrBuilder
    -0.53
    POSITIVE LOGITS
     blood
    0.85
    Blood
    0.82
    blood
    0.81
     Blood
    0.79
     sangue
    0.78
     BLOOD
    0.78
     bloody
    0.78
    bloody
    0.77
     sangre
    0.74
    BLOOD
    0.74
    Activations Density 0.016%

    No Known Activations