© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 2604
    Prev
    Next
    INDEX
    Explanations

    references to connections and transit routes in urban planning contexts

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

    city centers

    np_acts-logits-general · gemini-2.0-flash

    city centers and downtown districts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.68
    SourceChecksum
    -0.59
     ddelweddau
    -0.54
    rshire
    -0.52
    Portály
    -0.50
    esModule
    -0.50
     referenties
    -0.49
     الحره
    -0.49
    vole
    -0.48
     kho
    -0.48
    POSITIVE LOGITS
     downtown
    2.01
     Downtown
    1.62
    Downtown
    1.55
    downtown
    1.52
     Innenstadt
    1.28
     central
    1.15
     Altstadt
    1.06
     centro
    1.00
     center
    0.99
     centre
    0.99
    Activations Density 0.180%

    No Known Activations