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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9239
    Prev
    Next
    INDEX
    Explanations

    descriptions related to human activities in outdoor or public settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IMPORTED
    -0.52
    ISupport
    -0.48
    AntiForgeryToken
    -0.47
    מבר
    -0.47
    пель
    -0.47
    TagHelper
    -0.47
    nito
    -0.45
    HasBeenSet
    -0.45
    setViewportView
    -0.45
    fleur
    -0.44
    POSITIVE LOGITS
     streets
    2.20
     roads
    2.17
     street
    1.92
     road
    1.88
     Streets
    1.74
    streets
    1.66
     roadways
    1.66
    roads
    1.66
     Roads
    1.62
    street
    1.61
    Activations Density 0.207%

    No Known Activations