© 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. 11075
    Prev
    Next
    INDEX
    Explanations

    references to personal growth and realization of purpose

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

    the contraction "it's" and phrases expressing personal discovery or realization about identity and purpose.

    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
     disambiguazione
    -0.49
     applau
    -0.47
    出版年
    -0.46
    الإنجليزية
    -0.42
    tangentMode
    -0.42
     שוליים
    -0.40
    GEBURTSDATUM
    -0.40
    siasi
    -0.40
    nages
    -0.40
     compro
    -0.39
    POSITIVE LOGITS
     بالنسبة
    0.54
     taught
    0.53
     humbling
    0.47
     liberating
    0.47
     teach
    0.47
     affords
    0.46
     voelt
    0.46
    IndentedString
    0.45
     instilled
    0.44
     teaches
    0.44
    Activations Density 0.352%

    No Known Activations