© 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. 3-GEMMASCOPE-RES-16K
    6. 7957
    Prev
    Next
    INDEX
    Explanations

    programming syntax related to items and CSS styling

    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
    ésultats
    -0.93
    niſſe
    -0.88
    majánló
    -0.87
     laſſen
    -0.85
     müſſen
    -0.82
    idlertid
    -0.81
    mpagne
    -0.80
     ſind
    -0.79
    arangay
    -0.78
     שוליים
    -0.77
    POSITIVE LOGITS
    item
    1.25
     item
    0.69
    ITEM
    0.59
    .
    0.58
    Item
    0.58
     Item
    0.49
     (
    0.43
     
    0.43
    In
    0.42
     items
    0.41
    Activations Density 0.025%

    No Known Activations