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 - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12608
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe chaos and confusion

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

    associated with disorder or commotion

    np_acts-logits-general · gemini-2.0-flash

    chaos, crowds, noise, and disorder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URBANA
    -0.63
    ervazione
    -0.59
    θε
    -0.57
     læng
    -0.56
    ecore
    -0.55
     propOrder
    -0.55
     בעל
    -0.54
    Vidite
    -0.54
    ględ
    -0.53
    最快更新
    -0.52
    POSITIVE LOGITS
     chaos
    1.04
     caos
    0.95
     chaotic
    0.87
     cluttered
    0.78
     clutter
    0.76
     tumult
    0.76
     crowded
    0.74
     pile
    0.73
    chaos
    0.72
     throng
    0.71
    Activations Density 0.298%

    No Known Activations