Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 2340
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and data structures related to spreadsheets and CSV files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.61
    oredCriteria
    -0.61
     StatefulWidget
    -0.60
    ollectionView
    -0.59
     *)__
    -0.58
    borderSide
    -0.56
    Datuak
    -0.56
     guacamole
    -0.53
     AssemblyVersion
    -0.53
    withIdentifier
    -0.52
    POSITIVE LOGITS
     distanciation
    0.67
    Portály
    0.56
     elettrico
    0.53
    Filmografie
    0.52
    Rüyada
    0.52
     iconLine
    0.50
    Superintendent
    0.50
    scriptcase
    0.50
    Revenir
    0.49
    tagHelper
    0.49
    Activations Density 0.284%

    No Known Activations