Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 6369
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "house" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.77
     chimique
    -0.67
     alpina
    -0.62
     Neale
    -0.60
     culturelle
    -0.59
     atheists
    -0.58
     démocr
    -0.57
     Ensino
    -0.57
     étrangère
    -0.57
     químicas
    -0.56
    POSITIVE LOGITS
     house
    4.46
     House
    3.95
    House
    3.83
    house
    3.79
     HOUSE
    3.68
     houses
    3.57
    HOUSE
    3.46
     Houses
    3.13
    houses
    3.04
    Houses
    2.84
    Activations Density 0.080%

    No Known Activations