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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 14256
    Prev
    Next
    INDEX
    Explanations

    references to the Scanner class and its usage 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
     krak
    -0.64
     fous
    -0.58
     Unwin
    -0.57
     mę
    -0.56
    semver
    -0.55
     silk
    -0.55
     simb
    -0.54
    MemoryWarning
    -0.53
    ViewStyle
    -0.52
     nuclé
    -0.52
    POSITIVE LOGITS
    Scanner
    2.74
     Scanner
    2.43
     scanner
    1.82
    scanner
    1.66
     scanners
    1.44
    canner
    1.28
    SpringBootTest
    0.81
    SCAN
    0.80
    "]);
    
    0.80
    GEBURTSDATUM
    0.79
    Activations Density 0.026%

    No Known Activations