© 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. 37-GEMMASCOPE-RES-16K
    11. 4657
    Prev
    Next
    INDEX
    Explanations

    sentences that assert existence or define something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     therein
    -0.41
     dabei
    -0.38
     there
    -0.38
     đó
    -0.38
     this
    -0.38
    reordered
    -0.37
    ここでは
    -0.36
     those
    -0.36
    there
    -0.35
     Italijanski
    -0.35
    POSITIVE LOGITS
     happening
    0.81
     true
    0.75
     why
    0.72
    Happ
    0.70
     GenerationType
    0.65
    ConstraintMaker
    0.65
     geschieht
    0.64
    complexContent
    0.63
    happens
    0.62
    awtextra
    0.61
    Activations Density 0.248%

    No Known Activations