© 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. 1651
    Prev
    Next
    INDEX
    Explanations

    sequential markers or transitions in narratives or descriptions

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

    transitional words and phrases that connect sequential ideas or narrative flow within documents.

    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
     wcześniej
    -0.65
     wcześ
    -0.65
     daardoor
    -0.63
     hierbei
    -0.63
     obecnie
    -0.61
     eerder
    -0.61
     daher
    -0.59
     thus
    -0.58
     kiedyś
    -0.57
     antemano
    -0.56
    POSITIVE LOGITS
     proceeded
    1.06
     proceed
    0.94
     proceeding
    0.84
     proceeds
    0.83
    proceed
    0.81
     PROCEED
    0.77
     Proceed
    0.75
     procede
    0.72
     Proceeding
    0.69
    Proceed
    0.67
    Activations Density 0.609%

    No Known Activations