© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8101
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and motivations related to creative pursuits

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

    personal narratives about pursuing long-held childhood dreams or passions.

    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
     negociaciones
    -0.38
     duelo
    -0.37
     telefónica
    -0.35
     negociación
    -0.34
    HasAnnotation
    -0.34
    Примітки
    -0.33
    Notae
    -0.33
    together
    -0.33
     становника
    -0.32
     chuva
    -0.31
    POSITIVE LOGITS
     interest
    0.93
    interest
    0.88
     Interest
    0.85
     passion
    0.84
    Interest
    0.84
     passione
    0.82
     hobby
    0.81
     Interests
    0.79
     interests
    0.78
    interested
    0.77
    Activations Density 0.392%

    No Known Activations