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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 1948
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sit" and its variations, indicating a focus on sitting actions and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uolo
    -0.70
    ئي
    -0.63
     modo
    -0.61
     Valerio
    -0.59
     neod
    -0.58
     duidelijk
    -0.57
    addLine
    -0.56
    ⋙
    -0.56
    hql
    -0.56
    uey
    -0.56
    POSITIVE LOGITS
     sit
    1.70
     Sit
    1.67
    Sit
    1.64
     Sitting
    1.60
     sitting
    1.54
     sits
    1.53
    Sitting
    1.50
     SIT
    1.49
    sit
    1.38
    sitting
    1.35
    Activations Density 0.047%

    No Known Activations