© 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. 5621
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to spectroscopy and chemical analysis

    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
     ModelExpression
    -0.62
    хьтан
    -0.55
    FailureListener
    -0.53
     CreateTagHelper
    -0.52
    AndEndTag
    -0.51
    XmlEnum
    -0.50
     arşivlendi
    -0.50
     NSCoder
    -0.49
    RTEE
    -0.49
    PropertyChanging
    -0.49
    POSITIVE LOGITS
     IR
    2.59
     Ir
    2.58
     ir
    2.55
    Ir
    2.34
    IR
    2.11
    ir
    2.06
     Irwin
    1.81
     Irving
    1.78
     Irvin
    1.73
     infrared
    1.60
    Activations Density 1.033%

    No Known Activations