© 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. 11797
    Prev
    Next
    INDEX
    Explanations

    references to feelings of relief or requests for relief

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

    the word "relief" in legal, medical, and emotional contexts.

    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
     kasarigan
    -0.57
     estekak
    -0.57
    pushFollow
    -0.48
    toHaveBeenCalled
    -0.45
    ſt
    -0.45
    enterOuterAlt
    -0.45
     &___
    -0.45
    entarios
    -0.44
    idelity
    -0.44
     tuot
    -0.44
    POSITIVE LOGITS
     relief
    2.81
     Relief
    2.39
    relief
    2.36
    Relief
    2.34
     relieved
    2.25
     RELIEF
    2.22
     relieve
    2.05
     reliefs
    1.88
     relieving
    1.88
     relieves
    1.85
    Activations Density 0.237%

    No Known Activations