© 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. 3727
    Prev
    Next
    INDEX
    Explanations

    physical descriptions of characters

    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
    TabIndex
    -0.41
     ear
    -0.41
     Naked
    -0.39
    Buffered
    -0.39
    XmlRootElement
    -0.39
     Reb
    -0.39
    WaitGroup
    -0.38
    Naked
    -0.36
    Henry
    -0.36
     prés
    -0.36
    POSITIVE LOGITS
     pupils
    0.75
     hazel
    0.69
     almond
    0.64
     piercing
    0.62
     Pupils
    0.61
     pupil
    0.59
     eyes
    0.56
     penetrating
    0.55
     iris
    0.54
     кари
    0.54
    Activations Density 0.162%

    No Known Activations