© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3711
    Prev
    Next
    INDEX
    Explanations

    references to towns and related structures or concepts

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

    Follows "Town" and is related to "hall" or "houses"

    np_acts-logits-general · gemini-2.0-flash

    town hall or centre

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.76
     nonatomic
    -0.75
    zzleHttp
    -0.75
    XmlAccessorType
    -0.69
     MediatR
    -0.67
     &___
    -0.64
     Réponses
    -0.62
    expandindo
    -0.60
    oporosis
    -0.60
     ReactDOM
    -0.60
    POSITIVE LOGITS
     hall
    0.82
     centre
    0.78
    folk
    0.76
    hall
    0.75
     square
    0.70
     center
    0.69
    center
    0.67
     Hall
    0.66
    centre
    0.66
     squares
    0.63
    Activations Density 0.033%

    No Known Activations