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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 3785
    Prev
    Next
    INDEX
    Explanations

    references to television shows and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bő
    -0.55
     sposa
    -0.55
     femininos
    -0.54
     hés
    -0.53
     segno
    -0.52
     damska
    -0.51
     Bridal
    -0.50
     brides
    -0.50
     femininas
    -0.50
     tetanus
    -0.50
    POSITIVE LOGITS
     shows
    0.90
     program
    0.90
     ویکی‌پدی
    0.78
    tagHelperRunner
    0.78
     programa
    0.77
     programs
    0.76
     programme
    0.74
    émission
    0.74
    ohjel
    0.72
    shows
    0.72
    Activations Density 0.222%

    No Known Activations