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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15587
    Prev
    Next
    INDEX
    Explanations

    syntactic structures and symbols related to programming or logical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.77
     صوتيه
    -0.74
     المعيارى
    -0.73
    DebuggerNonUser
    -0.70
    NOPQRST
    -0.68
    contentLoaded
    -0.59
     فريبيس
    -0.58
    oredCriteria
    -0.58
    DeleteBehavior
    -0.56
     ویکی‌پدی
    -0.56
    POSITIVE LOGITS
     sentencing
    0.54
     flyknit
    0.53
     Depends
    0.52
    akte
    0.52
     Hege
    0.50
     shutterstock
    0.50
     doInBackground
    0.50
     Formulas
    0.50
     ExecuteAsync
    0.49
    Préparation
    0.49
    Activations Density 0.001%

    No Known Activations