© 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. 30-GEMMASCOPE-RES-16K
    11. 12557
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation associated with calculations

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

    Mathematical or statistical notation

    np_acts-logits-general · gemini-2.0-flash

    n followed by a number or variable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChromeDriver
    -0.53
    SqlClient
    -0.50
    batore
    -0.47
    Externé
    -0.47
     useStyles
    -0.44
    raborty
    -0.40
     Spielberg
    -0.40
    BorderFactory
    -0.40
    TSCA
    -0.40
    HttpPut
    -0.40
    POSITIVE LOGITS
    nonumber
    0.71
     nitrogen
    0.65
     numpy
    0.60
     naciones
    0.59
     Navy
    0.59
     Nathan
    0.59
     nación
    0.59
     necklace
    0.59
     Nintendo
    0.58
     neutron
    0.58
    Activations Density 2.915%

    No Known Activations