© 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. 105676
    Prev
    Next
    INDEX
    Explanations

    references to companies or publishers in documents

    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
     nahilalakip
    -0.91
    extAlignment
    -0.75
     المعيارى
    -0.71
     autorytatywna
    -0.69
    setupUi
    -0.69
    LookAnd
    -0.67
    setViewportView
    -0.67
     Infórmanos
    -0.66
     Normdatei
    -0.66
    RectangleBorder
    -0.65
    POSITIVE LOGITS
     Wiley
    0.73
    Wiley
    0.72
     Warner
    0.55
    Cisco
    0.49
     Cody
    0.48
     Norton
    0.47
     Etik
    0.47
     Moody
    0.46
    Warner
    0.46
     Cisco
    0.46
    Activations Density 0.024%

    No Known Activations