Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1730
    Prev
    Next
    INDEX
    Explanations

    concepts related to emotional and spiritual experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.69
    '])){
    
    -0.67
    migrationBuilder
    -0.66
    ValueStyle
    -0.65
     Pristupljeno
    -0.63
    :✨
    -0.62
    ConstraintMaker
    -0.61
     يتيمه
    -0.60
    脚注の使い方
    -0.58
    PDATE
    -0.58
    POSITIVE LOGITS
     traits
    0.66
    天生
    0.63
     innate
    0.62
     temperament
    0.61
     Traits
    0.55
     gifted
    0.54
     talents
    0.54
     personality
    0.53
     talent
    0.53
     Gifted
    0.51
    Activations Density 0.572%

    No Known Activations