© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104676
    Prev
    Next
    INDEX
    Explanations

    references to specific biological or medical terms and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     EconPapers
    -0.78
    tvguidetime
    -0.73
    expandindo
    -0.67
    GEBURTSDATUM
    -0.60
    AddTagHelper
    -0.55
    InitVars
    -0.53
    ValueStyle
    -0.51
     JpaRepository
    -0.49
    ритори
    -0.48
    TProtocol
    -0.48
    POSITIVE LOGITS
     íntima
    0.46
     discorso
    0.42
     ویکی‌پدیا
    0.40
    scheid
    0.40
    RegressionTest
    0.37
     íntimo
    0.37
    FontOfSize
    0.37
    Others
    0.36
     appunto
    0.35
     históricos
    0.35
    Activations Density 0.087%

    No Known Activations