© 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. 24-GEMMASCOPE-RES-16K
    11. 4175
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting related to mathematical or programming expressions

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

    Appears before a number

    np_acts-logits-general · gemini-2.0-flash

    numbers and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     becauſe
    -0.87
     themſelves
    -0.86
     himſelf
    -0.81
     myſelf
    -0.80
     Италијани
    -0.77
     whoſe
    -0.76
     Theſe
    -0.76
     theſe
    -0.74
     Monfieur
    -0.71
     ſeveral
    -0.71
    POSITIVE LOGITS
    <unused63>
    1.00
    <unused62>
    0.98
    <unused61>
    0.97
    <unused60>
    0.91
     mauvaises
    0.65
    gawai
    0.53
    存于互联网档案馆
    0.53
     PICTOGRAM
    0.52
     mauvaise
    0.50
     sèche
    0.49
    Activations Density 1.676%

    No Known Activations