© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3943
    Prev
    Next
    INDEX
    Explanations

    instances of the word "narrow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vah
    -0.62
     Civ
    -0.61
     Sandler
    -0.56
    Civ
    -0.56
     Sug
    -0.52
    хни
    -0.52
     Mil
    -0.52
     Pollock
    -0.51
    GUEST
    -0.51
    .+\
    -0.50
    POSITIVE LOGITS
     narrow
    0.99
    narrow
    0.99
     Narrow
    0.93
     narrower
    0.79
    Narrow
    0.78
     narrowly
    0.72
    complexContent
    0.70
    ChildScrollView
    0.69
    dialement
    0.68
    ->_
    0.67
    Activations Density 0.055%

    No Known Activations