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

    Neuronpedia

    APICircuit 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12758
    Prev
    Next
    INDEX
    Explanations

    references to urban environments and cities

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

    Names of cities

    np_acts-logits-general · gemini-2.0-flash

    city names and urban areas

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    -0.45
     Tim
    -0.44
    XmlAccessType
    -0.43
     صاد
    -0.42
     transfieras
    -0.42
    <?
    -0.40
    SuppressMessage
    -0.40
    êcher
    -0.39
    LabelTagHelper
    -0.39
     ProtoMessage
    -0.38
    POSITIVE LOGITS
     urban
    0.84
     city
    0.81
     metropolitan
    0.81
     metropolis
    0.77
     metropol
    0.71
     urbanos
    0.69
     urbana
    0.68
     urbanas
    0.68
    都市
    0.66
     urbano
    0.66
    Activations Density 0.388%

    No Known Activations