© 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. 20-GEMMASCOPE-RES-16K
    11. 8777
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational furniture and its functionality

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

    Furniture-related words

    np_acts-logits-general · gemini-2.0-flash

    storage furniture: drawers, shelves, cupboards

    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
    UpdateCommand
    -0.53
    DeleteCommand
    -0.53
    geth
    -0.51
    Diameter
    -0.51
    inflate
    -0.51
    InsertCommand
    -0.49
    CrossRef
    -0.49
     diamètre
    -0.49
     roundabout
    -0.48
    atlantic
    -0.47
    POSITIVE LOGITS
     drawers
    1.28
     shelves
    1.21
     cabinets
    1.16
     shelving
    1.14
     drawer
    1.14
     storage
    1.11
     cupboards
    1.05
     shelf
    1.04
     Shelves
    1.03
     closets
    1.02
    Activations Density 0.073%

    No Known Activations