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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 11691
    Prev
    Next
    INDEX
    Explanations

    instances of the word "close" or its variations, indicating closure or a related concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PhysRev
    -0.66
     HasFactory
    -0.66
    🏼
    -0.64
     CreateTagHelper
    -0.62
    󠁢
    -0.62
    󠁿
    -0.61
    Chips
    -0.59
    TypedDataSet
    -0.59
    ]--;
    -0.59
     ModelExpression
    -0.59
    POSITIVE LOGITS
     doors
    0.97
    doors
    0.82
     hermé
    0.73
     door
    0.72
     down
    0.69
     loop
    0.69
     Doors
    0.68
     tight
    0.67
    Doors
    0.67
     shut
    0.66
    Activations Density 0.081%

    No Known Activations