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. 7-GEMMASCOPE-RES-16K
    6. 7141
    Prev
    Next
    INDEX
    Explanations

    the word "under" in various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.84
    djangoproject
    -0.82
     Pingback
    -0.81
     Carlin
    -0.80
    RSpec
    -0.80
    SPJ
    -0.79
    ethnicity
    -0.78
    Mapp
    -0.76
     Spartans
    -0.76
    pyplot
    -0.75
    POSITIVE LOGITS
    Under
    1.81
     Under
    1.81
    under
    1.77
     under
    1.74
    UNDER
    1.69
     UNDER
    1.64
    neath
    1.28
     Underwood
    1.25
     unter
    1.21
    nder
    1.21
    Activations Density 0.111%

    No Known Activations