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. 11610
    Prev
    Next
    INDEX
    Explanations

    information related to urban transport and connectivity

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

    Mentions city centers or downtown areas

    np_acts-logits-general · gemini-2.0-flash

    downtown city center

    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
    SourceChecksum
    -0.83
     ddelweddau
    -0.68
     referenties
    -0.66
     iprot
    -0.61
     ***!
    -0.59
    Espèce
    -0.57
     virtuel
    -0.56
    OGND
    -0.51
     Normdatei
    -0.50
     propOrder
    -0.50
    POSITIVE LOGITS
     downtown
    2.11
    downtown
    1.73
     Downtown
    1.67
    Downtown
    1.60
     Innenstadt
    1.38
     town
    1.14
     city
    1.13
     Altstadt
    1.10
     central
    1.03
     centrum
    1.03
    Activations Density 0.166%

    No Known Activations