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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14625
    Prev
    Next
    INDEX
    Explanations

    themes related to neighborhood dynamics and interactions

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

    next door

    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
     mid
    -0.34
     final
    -0.32
    <?
    -0.31
     
    -0.30
     V
    -0.29
     Mittel
    -0.29
    mid
    -0.28
     G
    -0.28
     meta
    -0.28
    |
    -0.27
    POSITIVE LOGITS
     neighbors
    1.09
     neighbours
    1.04
     neighbor
    1.00
    Neighbors
    0.99
     Neighbors
    0.98
     neighbour
    0.96
     Nachbarn
    0.94
     Neighbor
    0.91
    neighbors
    0.89
    Neighbours
    0.88
    Activations Density 0.029%

    No Known Activations