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. 5-GEMMASCOPE-RES-16K
    6. 14501
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "perceive" and related concepts of perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Elton
    -0.72
     Weston
    -0.71
    lofen
    -0.69
    èvres
    -0.68
    afi
    -0.66
    deka
    -0.64
    Margot
    -0.64
     JTextArea
    -0.63
    arar
    -0.62
     shaker
    -0.62
    POSITIVE LOGITS
     perception
    1.05
    perception
    0.89
     perceive
    0.83
     Perception
    0.83
     HttpNotFound
    0.80
     perceptions
    0.79
     perceives
    0.78
     pitch
    0.77
    Perception
    0.75
     perceived
    0.74
    Activations Density 0.088%

    No Known Activations