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. 20-GEMMASCOPE-RES-16K
    6. 1805
    Prev
    Next
    INDEX
    Explanations

    terms related to particle filtering and smoothing techniques

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

    "Particle" or "Peanut" followed by related words

    np_acts-logits-general · gemini-2.0-flash

    particle filter or peanut butter

    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
     '\\;'
    -0.98
    URLException
    -0.93
    Demografia
    -0.90
    SourceChecksum
    -0.83
    BeginContext
    -0.82
    onedDateTime
    -0.74
    Filmographie
    -0.74
    ViewInit
    -0.73
     rospy
    -0.71
    rdı
    -0.71
    POSITIVE LOGITS
     swarms
    0.56
    anía
    0.56
     swarm
    0.55
    ころ
    0.54
    ỳnh
    0.54
    AppState
    0.53
    اسی
    0.52
     Ewig
    0.51
     faith
    0.50
    PCell
    0.50
    Activations Density 0.501%

    No Known Activations