© 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. 36-GEMMASCOPE-RES-16K
    11. 11585
    Prev
    Next
    INDEX
    Explanations

    references to hydrogen peroxide and its applications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.64
    mapStateToProps
    -0.57
    HasAnnotation
    -0.56
    basicConfig
    -0.54
    Pon
    -0.53
    Pilot
    -0.53
     Pilot
    -0.48
     Pon
    -0.47
    Pil
    -0.47
    Pap
    -0.46
    POSITIVE LOGITS
     PER
    1.94
     Per
    1.91
    Per
    1.81
    PER
    1.78
     Perry
    1.62
    per
    1.61
     Perkins
    1.57
     Perr
    1.55
     PERS
    1.49
     Pers
    1.48
    Activations Density 1.101%

    No Known Activations