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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5221
    Prev
    Next
    INDEX
    Explanations

    terms related to urban development and planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    fjspx
    -0.37
    utilisons
    -0.30
    ]")]
    -0.30
    
    -0.29
     classificação
    -0.29
    aronder
    -0.29
    elezo
    -0.28
     redacción
    -0.28
     clasificación
    -0.27
     ISSUED
    -0.27
    POSITIVE LOGITS
     urban
    0.89
     urbanization
    0.85
    urban
    0.75
    styleType
    0.68
    Urban
    0.68
     Urban
    0.68
     suburbs
    0.67
    urbs
    0.65
     cities
    0.65
    URBAN
    0.64
    Activations Density 0.178%

    No Known Activations