© 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. 5990
    Prev
    Next
    INDEX
    Explanations

    references to devices or apparatuses

    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
     lás
    -0.48
    StructEnd
    -0.45
    +#+#
    -0.44
    +:+
    -0.43
     mergeFrom
    -0.43
     administratif
    -0.41
     vorkommen
    -0.41
    這一
    -0.40
    retudo
    -0.40
     szuka
    -0.40
    POSITIVE LOGITS
     device
    3.94
    device
    3.69
     Device
    3.64
    Device
    3.48
     DEVICE
    3.19
     devices
    3.09
     Devices
    3.02
    DEVICE
    2.83
    devices
    2.63
    Devices
    2.63
    Activations Density 0.097%

    No Known Activations