© 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. 1289
    Prev
    Next
    INDEX
    Explanations

    references to articles, studies, and useful tips within a document

    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
     становника
    -0.36
    BeginContext
    -0.36
    EndGlobalSection
    -0.34
     OMITBAD
    -0.32
     Hälfte
    -0.32
     Bestandteil
    -0.29
    thansa
    -0.29
    PYX
    -0.28
     dostar
    -0.28
     للاسماء
    -0.28
    POSITIVE LOGITS
     article
    1.49
     infographic
    1.31
     blog
    1.22
     webinar
    1.18
     video
    1.15
     articles
    1.13
     podcast
    1.09
     tutorial
    1.09
     artikel
    1.07
    article
    1.01
    Activations Density 1.119%

    No Known Activations