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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43200
    Prev
    Next
    INDEX
    Explanations

    references to heaven and paradise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coaster
    -0.65
    Fitz
    -0.63
     Fitz
    -0.62
    RenderAtEndOf
    -0.61
     spind
    -0.60
     Furious
    -0.60
     CURL
    -0.60
    idoscope
    -0.59
    gerald
    -0.58
     Witcher
    -0.58
    POSITIVE LOGITS
     heaven
    1.65
     Heaven
    1.57
    heaven
    1.55
    Heaven
    1.51
     HEAVEN
    1.48
     heavens
    1.40
     Heavens
    1.29
     cielos
    1.23
     heavenly
    1.16
     cielo
    1.13
    Activations Density 0.008%

    No Known Activations