© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4385
    Prev
    Next
    INDEX
    Explanations

    indications of time and scheduling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases describing going to bed or sleeping.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.56
    Hauptartikel
    -0.48
    parsedMessage
    -0.46
     betweenstory
    -0.45
     CreateTagHelper
    -0.44
    (!__
    -0.43
    BeginContext
    -0.42
    ViewImports
    -0.42
    RenderAtEndOf
    -0.41
    出版年
    -0.40
    POSITIVE LOGITS
     bed
    1.61
     bedtime
    1.59
    Bed
    1.28
     Bed
    1.27
     sleep
    1.25
    bed
    1.25
     asleep
    1.19
     beds
    1.18
     BED
    1.18
     sleeping
    1.16
    Activations Density 0.173%

    No Known Activations