Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9864
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and locations related to higher education

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

    Washington D.C. and surrounding areas

    np_acts-logits-general · gemini-2.0-flash

    Washington DC area

    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
    noopener
    -0.60
    AndEndTag
    -0.59
    astify
    -0.58
    Bombay
    -0.54
     Marathi
    -0.52
     Durban
    -0.51
     Desai
    -0.50
     Kell
    -0.48
     Coimbatore
    -0.48
    zwald
    -0.48
    POSITIVE LOGITS
     Potomac
    1.35
     Washington
    1.32
    Washington
    1.24
     DC
    1.17
     Maryland
    1.11
     washington
    1.10
    DC
    1.04
     WASHINGTON
    1.03
     Bethesda
    0.99
     Redskins
    0.97
    Activations Density 0.400%

    No Known Activations