© 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. 1489
    Prev
    Next
    INDEX
    Explanations

    HTML attributes related to actions in form elements

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

    action or href attribute

    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
    ſelf
    -0.77
     protoimpl
    -0.69
     ſche
    -0.68
    ſelves
    -0.68
     queſta
    -0.67
     pleaſure
    -0.67
    reportWebVitals
    -0.66
    PreferredItem
    -0.65
     houſe
    -0.64
     wireType
    -0.63
    POSITIVE LOGITS
     action
    0.48
     inmediata
    0.46
     actie
    0.46
     immédi
    0.43
     href
    0.43
    action
    0.43
     ação
    0.42
     maternidade
    0.41
     acción
    0.40
     nubes
    0.40
    Activations Density 0.000%

    No Known Activations