© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 101489
    Prev
    Next
    INDEX
    Explanations

    technical terms and measurements related to data analysis and experimental results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    StructEnd
    -0.46
    AddTagHelper
    -0.42
     Theſe
    -0.42
    Tembelea
    -0.41
    writeField
    -0.41
     viſ
    -0.39
     Houſe
    -0.38
    InitVars
    -0.37
     Inſ
    -0.36
    -&
    -0.36
    POSITIVE LOGITS
     Administrativna
    0.73
     <>",
    0.54
    amitié
    0.50
     Keuangan
    0.49
     vegetación
    0.49
    ientôt
    0.48
    Personensuche
    0.48
     przesz
    0.48
     fazenda
    0.46
     Excerpt
    0.46
    Activations Density 0.024%

    No Known Activations