© 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. 8394
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "acute" and references to the Protobuf programming format

    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
    ChildScrollView
    -0.41
    VersionUID
    -0.41
     Herramientas
    -0.38
    Synopsis
    -0.38
    onViewCreated
    -0.38
    ContextHolder
    -0.38
     BorderRadius
    -0.36
     doInBackground
    -0.36
    нрави
    -0.35
    ställning
    -0.35
    POSITIVE LOGITS
    +#+
    0.70
     deadly
    0.69
    Cute
    0.63
     cute
    0.63
     lethal
    0.61
     IFTT
    0.61
    fraud
    0.61
    rotate
    0.60
     rotate
    0.59
    protobuf
    0.58
    Activations Density 0.115%

    No Known Activations