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. 20-GEMMASCOPE-RES-16K
    6. 8939
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "run."

    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
    saraba
    -0.76
    "}")
    -0.62
    theless
    -0.62
    Géographie
    -0.61
     Poon
    -0.59
     doubtnut
    -0.56
    ⓘ
    -0.55
    enumi
    -0.55
    .)}
    -0.54
     MyBatis
    -0.54
    POSITIVE LOGITS
     runs
    1.21
     Runs
    1.18
     run
    1.17
     Run
    1.15
     ran
    1.14
     running
    1.10
     Running
    1.09
     RUN
    1.09
    Runs
    1.08
    running
    1.08
    Activations Density 0.094%

    No Known Activations