© 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. 2-GEMMASCOPE-RES-16K
    11. 4433
    Prev
    Next
    INDEX
    Explanations

    references to mirrors and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.49
     JpaRepository
    -0.47
    cticut
    -0.46
     isSet
    -0.45
     blacksmith
    -0.44
    setVerticalGroup
    -0.44
    GOTREF
    -0.43
     FormData
    -0.43
    TryDecodeAsNil
    -0.42
     Италијани
    -0.42
    POSITIVE LOGITS
     mirror
    1.34
     Mirror
    1.25
     favorable
    1.23
    Mirror
    1.20
     favourable
    1.17
    mirror
    1.17
     reflection
    1.16
     reflected
    1.12
     mirrors
    1.11
     mirrored
    1.11
    Activations Density 0.170%

    No Known Activations