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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-GEMMASCOPE-RES-16K
    6. 9310
    Prev
    Next
    INDEX
    Explanations

    intensifiers, particularly variations of the word "quite"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whoſe
    -0.89
     Efq
    -0.86
     becauſe
    -0.84
     preſent
    -0.84
     bershka
    -0.80
     purpoſe
    -0.80
     itſelf
    -0.79
    seamnă
    -0.78
     flèche
    -0.77
     Theſe
    -0.77
    POSITIVE LOGITS
     quite
    2.20
     Quite
    2.10
    Quite
    2.05
    quite
    2.00
    Very
    1.55
     Very
    1.51
     muy
    1.39
    very
    1.29
     bastante
    1.24
     very
    1.19
    Activations Density 0.087%

    No Known Activations