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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15288
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical arrays and related notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.63
    <bos>
    -0.57
     هيا
    -0.53
    ปรับ
    -0.53
    kuper
    -0.52
    adaptiveStyles
    -0.51
     <",
    -0.50
    chimp
    -0.49
     waarop
    -0.49
    zubauen
    -0.49
    POSITIVE LOGITS
    array
    1.20
     array
    0.83
    ValueStyle
    0.71
     autorytatywna
    0.68
    Array
    0.67
     arrays
    0.66
     Array
    0.64
    MemoryWarning
    0.63
    arrays
    0.62
    endphp
    0.62
    Activations Density 0.050%

    No Known Activations