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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 117379
    Prev
    Next
    INDEX
    Explanations

    sequences of events in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    UnsafeEnabled
    -0.36
    ClientSize
    -0.36
     idag
    -0.34
    Aholisi
    -0.34
    يكب
    -0.34
    Zubereitung
    -0.33
     dess
    -0.33
    ViewImports
    -0.33
    一个月
    -0.33
    didSet
    -0.32
    POSITIVE LOGITS
    writeFieldEnd
    0.54
     houſe
    0.50
     חיצוניים
    0.49
    starch
    0.48
    +#+#
    0.47
    scribers
    0.47
    matite
    0.45
     Houſe
    0.44
    Билгалдахарш
    0.44
     وتسجيلات
    0.44
    Activations Density 0.020%

    No Known Activations