© 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-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6804
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical notations or symbols used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſind
    -0.80
     queſta
    -0.77
    iſen
    -0.74
     betweenstory
    -0.74
    quelize
    -0.72
    ChildScrollView
    -0.71
     '\\;'
    -0.69
     bershka
    -0.69
     tfsi
    -0.68
    Chham
    -0.68
    POSITIVE LOGITS
    hline
    2.03
    <tr>
    0.50
    1
    0.50
    tabular
    0.49
    cline
    0.45
    <strong>
    0.44
    0
    0.44
    A
    0.43
    hi
    0.43
    <em>
    0.43
    Activations Density 0.032%

    No Known Activations