© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1760
    Prev
    Next
    INDEX
    Explanations

    various types of syntax or formatting used in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX code or mathematical formulas

    np_acts-logits-general · gemini-2.0-flash

    invalid argument exception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.66
    ↵↵↵
    -0.60
     ’
    -0.59
     col
    -0.56
    vikle
    -0.56
     ~
    -0.54
     par
    -0.54
     restos
    -0.54
     fast
    -0.54
     high
    -0.54
    POSITIVE LOGITS
     Sodom
    1.07
    theless
    0.95
     Ather
    0.92
     Rhy
    0.90
     apothe
    0.88
    __':
    0.86
    DeleteBehavior
    0.86
     Khrushchev
    0.86
     loch
    0.85
     getItemId
    0.85
    Activations Density 0.002%

    No Known Activations