Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 113886
    Prev
    Next
    INDEX
    Explanations

    various proper nouns, particularly names of places and significant entities

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

    names of cities and regions

    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
    contentLoaded
    -0.66
    цездатний
    -0.64
     AssemblyCulture
    -0.62
    Hochspringen
    -0.56
    NameInMap
    -0.56
    WireFormatLite
    -0.55
    expandindo
    -0.54
    хьтан
    -0.54
     nakalista
    -0.51
    featureID
    -0.50
    POSITIVE LOGITS
     city
    0.76
     City
    0.63
     residents
    0.62
     town
    0.60
     local
    0.59
    City
    0.58
     County
    0.57
     città
    0.56
     county
    0.56
     cidade
    0.52
    Activations Density 0.041%

    No Known Activations