© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3310
    Prev
    Next
    INDEX
    Explanations

    terms related to outdoor spaces and access points

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

    patios, decks, or balconies

    np_acts-logits-general · gemini-2.0-flash

    outdoor spaces, balconies, patios, decks

    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
     Centres
    -0.47
     centers
    -0.46
    zentrum
    -0.46
     centres
    -0.45
    ionato
    -0.43
     Escolar
    -0.43
     pari
    -0.41
     boucles
    -0.41
    сле
    -0.40
     koni
    -0.40
    POSITIVE LOGITS
     patio
    1.56
     outdoor
    1.55
     balcony
    1.46
     terrace
    1.39
     patios
    1.33
     balconies
    1.30
     Patio
    1.28
     outdoors
    1.27
    Outdoor
    1.26
    outdoor
    1.25
    Activations Density 0.070%

    No Known Activations