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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 4156
    Prev
    Next
    INDEX
    Explanations

    references to political entities and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     farmhouse
    -0.72
    expandindo
    -0.63
     Farmhouse
    -0.62
    Agr
    -0.61
     Agr
    -0.60
     farm
    -0.58
    UseVisualStyle
    -0.58
     Farm
    -0.57
    Farm
    -0.55
    farm
    -0.55
    POSITIVE LOGITS
     city
    2.56
     City
    2.55
    City
    2.37
     CITY
    2.24
     Mayor
    2.23
    city
    2.20
    CITY
    2.16
    Mayor
    2.10
     mayor
    1.89
     mayoral
    1.86
    Activations Density 0.400%

    No Known Activations