© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5395
    Prev
    Next
    INDEX
    Explanations

    instances of foundational or organizational beginnings, particularly those related to companies or associations

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

    "Founded" or "was founded"

    np_acts-logits-general · gemini-2.0-flash

    establishment origin

    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
    antMatchers
    -0.64
    RenderAtEndOf
    -0.63
     cref
    -0.60
     AssemblyProduct
    -0.58
     upcoming
    -0.54
     GetEnumerator
    -0.52
     reschedule
    -0.51
    ernalia
    -0.50
    WebServlet
    -0.50
     passim
    -0.49
    POSITIVE LOGITS
     ursprünglich
    1.08
     originally
    0.92
     Originally
    0.90
    originally
    0.87
     originalmente
    0.86
     ursprünglichen
    0.83
     inicialmente
    0.80
     awalnya
    0.78
    Originally
    0.77
    元々
    0.77
    Activations Density 0.318%

    No Known Activations