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. 16-GEMMASCOPE-RES-16K
    6. 1890
    Prev
    Next
    INDEX
    Explanations

    references to film and performance critiques

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

    Punctuation followed by lowercase letters

    np_acts-logits-general · gemini-2.0-flash

    quotes and apostrophes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     métallique
    -0.79
     enfans
    -0.73
     réglable
    -0.71
     nakalista
    -0.71
     isolé
    -0.69
     GenerationType
    -0.69
    ViewImports
    -0.68
     nemici
    -0.67
     militaires
    -0.67
     réguli
    -0.66
    POSITIVE LOGITS
     romantic
    0.57
     rom
    0.56
     lovel
    0.55
     Seinfeld
    0.53
     sentimental
    0.47
    MessageTagHelper
    0.46
     indie
    0.45
     quirky
    0.44
     jil
    0.43
     street
    0.43
    Activations Density 0.212%

    No Known Activations