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. 20-GEMMASCOPE-RES-16K
    6. 14766
    Prev
    Next
    INDEX
    Explanations

    essential elements related to rendering conditions and expectations in structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by DNA, Q, or --

    np_acts-logits-general · gemini-2.0-flash

    viral components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mères
    -0.62
     démocr
    -0.57
     kasarigan
    -0.57
     Italijanski
    -0.55
     Мексичка
    -0.54
     estekak
    -0.54
     forêts
    -0.52
    matchCondition
    -0.51
    astă
    -0.50
     pères
    -0.48
    POSITIVE LOGITS
     components
    1.43
    各项
    1.40
     various
    1.35
     elements
    1.32
     items
    1.31
     stuff
    1.30
    ต่างๆ
    1.29
    various
    1.22
     everything
    1.16
     stuffs
    1.15
    Activations Density 0.964%

    No Known Activations