© 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. 28-GEMMASCOPE-RES-16K
    11. 7298
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations

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

    Mathematical notation within text

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -0.75
     الرياضيه
    -0.58
     MainAxisSize
    -0.55
     EClass
    -0.53
     IBOutlet
    -0.53
    posedge
    -0.52
    makeConstraints
    -0.52
    IBarButtonItem
    -0.51
    UserScript
    -0.50
    <?
    -0.50
    POSITIVE LOGITS
     precisione
    0.47
     two
    0.37
    gfx
    0.36
     prefeitura
    0.35
    <u>
    0.35
     justified
    0.35
     tenuta
    0.34
     organizing
    0.34
     Leder
    0.34
    opoly
    0.34
    Activations Density 0.132%

    No Known Activations