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. 16053
    Prev
    Next
    INDEX
    Explanations

    syntactic structures and data management operations in programming code

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

    table columns

    np_acts-logits-general · gemini-2.0-flash

    column and columns

    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
     שוליים
    -0.67
    
    -0.56
     للمعارف
    -0.53
     CreateTagHelper
    -0.53
    complexContent
    -0.52
    PerformLayout
    -0.47
    Crossref
    -0.46
     neceff
    -0.46
    carina
    -0.45
     disponibilités
    -0.45
    POSITIVE LOGITS
     column
    2.19
     columns
    2.08
     Column
    1.73
    column
    1.73
     columnas
    1.72
     Columns
    1.71
     columna
    1.63
    Column
    1.59
     coluna
    1.57
     COLUMN
    1.56
    Activations Density 0.315%

    No Known Activations