© 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. 11385
    Prev
    Next
    INDEX
    Explanations

    evidence of social commentary on race and identity issues

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

    words that appear at the boundaries between sentences or clauses, particularly commas and conjunctions connecting independent thoughts.

    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
    AsUp
    -0.41
    XmlAccessorType
    -0.41
    Билгалдахарш
    -0.37
     contemporáneo
    -0.35
    Izvori
    -0.35
    specialchars
    -0.35
    nodoc
    -0.34
    GEBURTSDATUM
    -0.34
    åk
    -0.32
     bezeichneter
    -0.32
    POSITIVE LOGITS
     now
    4.06
     ahora
    3.22
     теперь
    3.09
    now
    3.02
     maintenant
    2.89
     sekarang
    2.73
     nyní
    2.70
    Now
    2.67
     Now
    2.66
     agora
    2.64
    Activations Density 2.529%

    No Known Activations