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. 11-GEMMASCOPE-RES-16K
    6. 5659
    Prev
    Next
    INDEX
    Explanations

    elements related to outdoor spaces and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.75
    ⓧ
    -0.74
     Roskov
    -0.70
    AddTagHelper
    -0.68
     صوتيه
    -0.66
     ProtoMessage
    -0.65
    DotNetBar
    -0.65
    Hentet
    -0.61
    enderror
    -0.61
     Wiktionnaire
    -0.60
    POSITIVE LOGITS
     patio
    0.91
     Patio
    0.85
     garden
    0.83
     outdoor
    0.82
     backyard
    0.75
     yard
    0.75
    Patio
    0.74
     gardens
    0.72
     patios
    0.71
     courtyard
    0.70
    Activations Density 0.078%

    No Known Activations