© 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. 31-GEMMASCOPE-RES-16K
    11. 9973
    Prev
    Next
    INDEX
    Explanations

    expressions indicating transitions, intentions, and significant life changes

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

    phrases indicating imminent action or transition using "about to" constructions.

    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
     сначала
    -0.35
    ONAUT
    -0.33
    chaus
    -0.32
    work
    -0.31
     ederim
    -0.31
    CHIN
    -0.31
    以降
    -0.30
    hynch
    -0.30
    ęgn
    -0.29
    ⊱
    -0.29
    POSITIVE LOGITS
    即将
    1.46
     impending
    1.29
     sắp
    1.24
     imminent
    1.19
     soon
    1.12
     ready
    1.08
     upcoming
    1.06
     nearing
    1.05
    もうすぐ
    1.02
     approaching
    1.00
    Activations Density 0.412%

    No Known Activations