© 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. 5-GEMMASCOPE-RES-16K
    11. 3052
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "house" or its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ergies
    -0.94
     reaſon
    -0.88
     Raptors
    -0.85
     geox
    -0.84
     ſmall
    -0.83
     Avid
    -0.83
    atonin
    -0.82
     twine
    -0.82
     fidélité
    -0.82
     sequins
    -0.82
    POSITIVE LOGITS
     house
    2.22
     House
    2.10
    House
    1.95
     houses
    1.91
    house
    1.89
     HOUSE
    1.76
     Houses
    1.69
    HOUSE
    1.68
    houses
    1.62
    Houses
    1.60
    Activations Density 0.048%

    No Known Activations