© 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. 33-GEMMASCOPE-RES-16K
    6. 11428
    Prev
    Next
    INDEX
    Explanations

    mentions of impactful events or significant trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     afterwards
    -0.55
    <?
    -0.48
     resourceCulture
    -0.46
     afterward
    -0.46
    튿
    -0.45
    endregion
    -0.43
     thereafter
    -0.43
     later
    -0.41
    initializeApp
    -0.40
    RatingBar
    -0.40
    POSITIVE LOGITS
     infatti
    0.94
    Indeed
    0.92
     examples
    0.90
     Indeed
    0.88
     example
    0.88
     ejemplo
    0.87
     Beispiel
    0.84
     Beispiele
    0.84
     esempio
    0.82
     indeed
    0.81
    Activations Density 0.448%

    No Known Activations