© 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. 12-GEMMASCOPE-RES-16K
    6. 4455
    Prev
    Next
    INDEX
    Explanations

    variations of the word "only" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moindre
    -0.35
     suelo
    -0.32
     stratégique
    -0.32
    postIndex
    -0.31
     suite
    -0.31
     cascada
    -0.30
    writeFieldEnd
    -0.30
     traditionnelle
    -0.29
     abiertos
    -0.29
     chaleureux
    -0.29
    POSITIVE LOGITS
     exclusively
    0.94
     only
    0.87
    only
    0.86
     ONLY
    0.85
    ONLY
    0.83
    Only
    0.81
     Only
    0.81
     Exclu
    0.78
    exclu
    0.78
     solely
    0.77
    Activations Density 0.765%

    No Known Activations