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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105154
    Prev
    Next
    INDEX
    Explanations

    references to neighborhood locations and communities within a city

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    رشف
    -0.51
     aş
    -0.35
    AutoField
    -0.35
     dés
    -0.34
    nalités
    -0.31
    Diwedd
    -0.30
    Vanjske
    -0.30
    publicain
    -0.29
     tỏ
    -0.29
     kapas
    -0.28
    POSITIVE LOGITS
     suburb
    0.72
     neighborhoods
    0.72
     area
    0.63
     suburbs
    0.62
     neighborhood
    0.60
     área
    0.59
     neighbourhoods
    0.59
    downtown
    0.58
     downtown
    0.58
     Midtown
    0.57
    Activations Density 0.037%

    No Known Activations