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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 67609
    Prev
    Next
    INDEX
    Explanations

    terms and structures related to the build and makefile processes in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     ModelExpression
    -0.99
    StoryboardSegue
    -0.73
    webElementXpaths
    -0.69
    EDEFAULT
    -0.68
    styleType
    -0.68
    BeginContext
    -0.66
     المعيارى
    -0.66
    
    -0.65
    RectangleBorder
    -0.60
    twimg
    -0.60
    POSITIVE LOGITS
     infraestructura
    0.35
     gérer
    0.34
    บู
    0.33
     stratégique
    0.33
     asistente
    0.32
     logística
    0.32
     mères
    0.32
     ingeniería
    0.32
    System
    0.32
     CanadaChoose
    0.32
    Activations Density 0.077%

    No Known Activations