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. 2737
    Prev
    Next
    INDEX
    Explanations

    connections to alternatives and combinations in formulations or compositions

    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
    UnsafeEnabled
    -0.55
    Purity
    -0.54
     Wikispecies
    -0.47
     electrocardio
    -0.46
     kater
    -0.45
     dezvol
    -0.43
     Créez
    -0.43
     stamens
    -0.43
     részt
    -0.42
     Wiesen
    -0.42
    POSITIVE LOGITS
     AssemblyProduct
    0.83
    queryInterface
    0.82
    parsedMessage
    0.75
    modelBuilder
    0.74
    phite
    0.70
    HasAnnotation
    0.69
    setViewportView
    0.69
    UnusedPrivate
    0.69
     tartalomajánló
    0.68
    yntaxException
    0.68
    Activations Density 0.251%

    No Known Activations