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. 114620
    Prev
    Next
    INDEX
    Explanations

    arithmetic and mathematical operations

    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
    parsedMessage
    -0.72
    الحياه
    -0.60
    AndEndTag
    -0.58
     &___
    -0.56
    DataAnnotations
    -0.55
    writeField
    -0.54
    fromnode
    -0.52
    EndGlobalSection
    -0.50
    formik
    -0.49
     desmotivaciones
    -0.48
    POSITIVE LOGITS
     drehen
    0.37
    Mga
    0.35
    Vari
    0.32
     defaultstate
    0.31
    źródło
    0.30
     isNameExpr
    0.30
    REC
    0.29
     Numerade
    0.29
    டைய
    0.29
    Seek
    0.29
    Activations Density 0.009%

    No Known Activations