© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 40235
    Prev
    Next
    INDEX
    Explanations

    function definitions for component creation

    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
     للمعارف
    -0.69
    Slf
    -0.57
    PathVariable
    -0.54
     فريبيس
    -0.53
    bufio
    -0.52
    __':
    -0.50
     صوتيه
    -0.49
    }`}>
    -0.49
    gods
    -0.48
    +#+#
    -0.48
    POSITIVE LOGITS
    createComponent
    4.66
    Component
    0.88
     component
    0.84
     Component
    0.83
    COMPONENT
    0.77
     COMPONENT
    0.75
     componente
    0.75
    component
    0.75
     Components
    0.72
     components
    0.71
    Activations Density 0.000%

    No Known Activations