© 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. 10145
    Prev
    Next
    INDEX
    Explanations

    references to judging and evaluation in a competitive context

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

    words and phrases related to judging, evaluation, and assessment of people or talent.

    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
     Paglinawan
    -0.45
     utafitiHapana
    -0.43
     NUKAT
    -0.41
    дарь
    -0.39
    oa̍t
    -0.39
    precip
    -0.36
    Maintenance
    -0.35
    Trou
    -0.35
    thâu
    -0.34
     GenerationType
    -0.34
    POSITIVE LOGITS
     judging
    1.97
     judges
    1.83
     judge
    1.82
     judged
    1.77
     evaluation
    1.76
     judgement
    1.70
     judgment
    1.66
     evalu
    1.63
     evaluating
    1.62
    jud
    1.60
    Activations Density 0.531%

    No Known Activations