© 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. 10397
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation marks, particularly commas and periods

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

    commas used to separate clauses or list items within sentences.

    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
    verwijspagina
    -0.55
    ,
    -0.52
     ✭✭
    -0.52
    锈钢
    -0.50
     Roskov
    -0.48
     EconPapers
    -0.48
     dic
    -0.46
    rungsseite
    -0.45
     AssemblyCompany
    -0.44
    Aholisi
    -0.43
    POSITIVE LOGITS
     aikana
    0.69
     boyunca
    0.63
     podczas
    0.63
     előtt
    0.60
     wobec
    0.59
     kautta
    0.59
     ennen
    0.59
     kanssa
    0.57
     during
    0.55
     nedeniyle
    0.54
    Activations Density 0.593%

    No Known Activations