© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 10281
    Prev
    Next
    INDEX
    Explanations

    symbols related to mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -1.27
    windowFixed
    -1.18
     linkovi
    -1.16
     $_"
    -1.16
     houſe
    -1.16
    Portail
    -1.14
     pleaſure
    -1.14
    Демографія
    -1.13
    expandindo
    -1.13
     Houſe
    -1.10
    POSITIVE LOGITS
     \
    0.77
    {\
    0.76
     I
    0.71
    <strong>
    0.69
     
    0.68
    <h3>
    0.67
    <tr>
    0.67
     (
    0.65
    \
    0.63
     &
    0.62
    Activations Density 0.071%

    No Known Activations