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. 1373
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structures in code

    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
     оригіналу
    -0.94
     InputDecoration
    -0.80
     المعيارى
    -0.75
     BoxDecoration
    -0.72
    HasForeignKey
    -0.68
    CloseOperation
    -0.67
     الرياضيه
    -0.65
    ConstraintMaker
    -0.61
    IsMutable
    -0.61
    LOAT
    -0.61
    POSITIVE LOGITS
     fleste
    0.47
     démocr
    0.46
    Manbalar
    0.45
    rzost
    0.43
    IndentedString
    0.43
     estimés
    0.42
     mål
    0.42
     fédé
    0.42
    qtype
    0.41
     rigide
    0.40
    Activations Density 0.126%

    No Known Activations