© 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. 8453
    Prev
    Next
    INDEX
    Explanations

    descriptions related to the layout and features of a house

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

    Text after "bedroom" or related to bedrooms

    np_acts-logits-general · gemini-2.0-flash

    bedroom

    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
    setVerticalGroup
    -0.58
    !*\
    -0.55
    weisungen
    -0.52
     dAtA
    -0.49
    StreetMap
    -0.49
     händer
    -0.49
    BorderLayout
    -0.48
     piti
    -0.48
    sitions
    -0.48
    uttg
    -0.48
    POSITIVE LOGITS
     незавершена
    0.70
    writeFieldEnd
    0.65
     Bedrooms
    0.64
     bedrooms
    0.62
     Bedroom
    0.59
     bedroom
    0.59
    Bedrooms
    0.58
    rollup
    0.58
     ebenfalls
    0.56
     prostor
    0.55
    Activations Density 0.019%

    No Known Activations