© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 3854
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting indicators within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -1.03
     disambiguazione
    -0.98
    queryInterface
    -0.88
     kaarangay
    -0.88
     utafitiHapana
    -0.88
    IntoConstraints
    -0.88
    rungsseite
    -0.87
     AssemblyCulture
    -0.85
    RectangleBorder
    -0.85
    expandindo
    -0.83
    POSITIVE LOGITS
     originally
    0.59
    originally
    0.55
     known
    0.54
    łada
    0.53
     perfección
    0.52
    ซึ่ง
    0.52
     ausgestattet
    0.49
     six
    0.48
     is
    0.48
    Originally
    0.47
    Activations Density 0.383%

    No Known Activations