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. 131023
    Prev
    Next
    INDEX
    Explanations

    string concatenations and logging statements in code

    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
     pinulongan
    -0.52
    adaptiveStyles
    -0.49
    pecabe
    -0.49
    astéroïdes
    -0.48
    majánló
    -0.47
    épend
    -0.46
     leaſt
    -0.45
    
    -0.45
    ntä
    -0.44
    istungs
    -0.43
    POSITIVE LOGITS
    withIdentifier
    0.50
    GIVEREF
    0.42
    archiviato
    0.41
    UMBUS
    0.39
    writeField
    0.39
     affirmative
    0.38
    ScopeManager
    0.37
    cin
    0.37
     ويكيميديا
    0.35
     bummer
    0.35
    Activations Density 0.014%

    No Known Activations