© 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-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6720
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming symbols related to operations and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.50
    noopener
    -0.39
    rau
    -0.39
    Kob
    -0.39
    copg
    -0.38
     Stron
    -0.38
     Neu
    -0.37
                         
    -0.37
     Kemp
    -0.36
    tailed
    -0.36
    POSITIVE LOGITS
    ๆ
    0.66
     ​​
    0.65
     enfans
    0.64
    +#+
    0.63
     incomplète
    0.63
     Wikiseite
    0.62
     disambiguazione
    0.61
     illustrationer
    0.61
    SourceChecksum
    0.58
     Bewohner
    0.57
    Activations Density 2.026%

    No Known Activations