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. 20-GEMMASCOPE-RES-16K
    6. 8999
    Prev
    Next
    INDEX
    Explanations

    locations and events relevant to a specific community or destination

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

    Singapore and its institutions

    np_acts-logits-general · gemini-2.0-flash

    Singapore universities and East locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     jagung
    -0.55
     rumour
    -0.54
     optimisation
    -0.53
    initialise
    -0.53
     learnt
    -0.52
     generalised
    -0.50
    eavour
    -0.49
    rsiniz
    -0.49
     customised
    -0.49
     şi
    -0.49
    POSITIVE LOGITS
     Singapore
    0.94
     Singapur
    0.88
     Jefus
    0.87
     singapore
    0.85
     themſelves
    0.85
    Singapore
    0.81
     Singapura
    0.80
     himſelf
    0.76
     Efq
    0.76
     Anſ
    0.75
    Activations Density 0.115%

    No Known Activations