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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 14401
    Prev
    Next
    INDEX
    Explanations

    elements related to emotional depth and complexity in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cioè
    -0.58
     such
    -0.55
     monnaie
    -0.55
     very
    -0.54
     honte
    -0.52
     paroisse
    -0.51
     vœux
    -0.51
     prisonniers
    -0.51
     comunale
    -0.51
     personnes
    -0.51
    POSITIVE LOGITS
    yet
    0.85
     yet
    0.84
    Yet
    0.79
    ValueStyle
    0.77
    ReusableCell
    0.75
     Pourtant
    0.73
     Yet
    0.71
    SpringBootTest
    0.70
    MLLoader
    0.68
    ₂+
    0.67
    Activations Density 0.322%

    No Known Activations