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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 38748
    Prev
    Next
    INDEX
    Explanations

    varying levels of difficulty and challenges in tasks or concepts

    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
     surla
    -0.71
     <<<<<<<<<<<<<<
    -0.69
    __(/*!
    -0.68
    ollectionView
    -0.68
    Geplaatst
    -0.62
    mobileqq
    -0.60
    fml
    -0.59
     Италијани
    -0.59
    милия
    -0.57
    Tikang
    -0.56
    POSITIVE LOGITS
     difficult
    1.24
    difficult
    1.15
     Difficult
    1.13
    Difficult
    1.05
     difficulty
    0.96
     harder
    0.96
     schwierig
    0.94
     challenging
    0.94
     impossible
    0.93
     schwier
    0.91
    Activations Density 0.087%

    No Known Activations