© 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. 3-GEMMASCOPE-RES-16K
    11. 6018
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "fully" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleable
    -0.57
    ViewImports
    -0.52
    quelize
    -0.48
    <bos>
    -0.45
    odorante
    -0.44
     occafion
    -0.43
    SequentialGroup
    -0.42
     Perſ
    -0.41
    ServiceTest
    -0.41
    HasColumnName
    -0.40
    POSITIVE LOGITS
     fully
    3.81
     Fully
    3.64
    Fully
    3.45
    fully
    2.39
    FULLY
    2.19
     plenamente
    2.16
     pleinement
    2.05
     полностью
    2.02
     sepenuhnya
    1.93
     entièrement
    1.85
    Activations Density 0.069%

    No Known Activations