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 - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 4278
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and functions, particularly those concerning thread management and data storage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    localctx
    -0.65
    CompilerServices
    -0.62
    __":
    
    -0.59
    __":
    -0.56
    참고
    -0.52
    __':
    -0.52
     podjela
    -0.52
    nodoc
    -0.50
     autorytatywna
    -0.49
    Tembelea
    -0.49
    POSITIVE LOGITS
    sizeCache
    0.63
    Hochspringen
    0.62
    الحياه
    0.61
    abestanden
    0.59
     vives
    0.58
    IsMutable
    0.56
     nahilalakip
    0.54
     समीक्षाएं
    0.53
    odend
    0.53
     acciaio
    0.53
    Activations Density 0.547%

    No Known Activations