© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5682
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases indicating the existence or occurrence of 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
    audiovisuel
    -0.41
     Defined
    -0.39
    ChildScrollView
    -0.38
    :][
    -0.36
    defined
    -0.36
    whose
    -0.35
     involuc
    -0.35
    involved
    -0.35
     gril
    -0.34
    PerformLayout
    -0.33
    POSITIVE LOGITS
     indicative
    0.82
     conducive
    0.80
     beneficial
    0.76
     advantageous
    0.73
     detrimental
    0.72
     reflected
    0.71
     consistent
    0.70
     enough
    0.70
     EconPapers
    0.68
     sufficient
    0.68
    Activations Density 0.791%

    No Known Activations