© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 42086
    Prev
    Next
    INDEX
    Explanations

    references to new or recent studies or articles

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

    new/recent reports and studies

    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
     Autorizaciones
    -0.81
    IUrlHelper
    -0.77
     &___
    -0.76
    Personendaten
    -0.72
     '\\;'
    -0.69
     nahilalakip
    -0.68
     Infórmanos
    -0.68
    Personensuche
    -0.67
     autorytatywna
    -0.67
     surla
    -0.66
    POSITIVE LOGITS
     report
    0.54
     survey
    0.49
     analysis
    0.47
     video
    0.45
     exploratory
    0.44
     research
    0.44
     tweet
    0.42
     pictorial
    0.41
     study
    0.41
     magazine
    0.41
    Activations Density 0.029%

    No Known Activations