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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15696
    Prev
    Next
    INDEX
    Explanations

    references to the uncertainty principle in physics

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

    quantum physics theories and principles

    np_acts-logits-general · gemini-2.0-flash

    uncertainty principle, quantum gravity, laws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    醐
    -0.42
     OPTIM
    -0.39
     سف
    -0.35
    Optim
    -0.34
     optimis
    -0.33
     Stirn
    -0.33
    akterysty
    -0.32
     Aprove
    -0.32
    باش
    -0.32
    ="../../
    -0.32
    POSITIVE LOGITS
     ब्रेकडाउन
    0.73
     theories
    0.72
     theory
    0.71
     laws
    0.69
     Theory
    0.62
    laws
    0.62
    theory
    0.62
     teori
    0.60
     Theories
    0.60
     Laws
    0.59
    Activations Density 0.570%

    No Known Activations