© 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. 15714
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "with."

    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
     purpoſe
    -0.81
     houſe
    -0.79
     ſte
    -0.78
     pleaſure
    -0.77
     poffible
    -0.77
     enfans
    -0.75
     faſt
    -0.72
     ſtate
    -0.71
    ſelf
    -0.71
     ſta
    -0.71
    POSITIVE LOGITS
    with
    1.14
     WITH
    0.99
     with
    0.98
    With
    0.95
     With
    0.94
    WITH
    0.91
     avec
    0.88
     dengan
    0.82
     עם
    0.82
    dengan
    0.81
    Activations Density 0.399%

    No Known Activations