© 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. 11-GEMMASCOPE-RES-16K
    11. 10129
    Prev
    Next
    INDEX
    Explanations

    frequently used adverbs indicating regularity or commonality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.80
    ConstraintMaker
    -0.62
    PreExecute
    -0.59
    ximately
    -0.57
     TestBed
    -0.54
    ſelf
    -0.53
    ImageIO
    -0.52
    shiro
    -0.52
     HomeComponent
    -0.51
    wapV
    -0.50
    POSITIVE LOGITS
     often
    1.47
    often
    1.35
    Often
    1.26
     Often
    1.23
     frequently
    1.16
     často
    1.14
     frequentemente
    1.13
    frequently
    1.11
     souvent
    1.10
     spesso
    1.10
    Activations Density 0.136%

    No Known Activations