© 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. 8-GEMMASCOPE-RES-16K
    11. 5661
    Prev
    Next
    INDEX
    Explanations

    words that indicate action or activity in the context of relationships and interactions

    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
    LookAnd
    -0.88
     itſelf
    -0.79
    ViewFeatures
    -0.79
     oprot
    -0.77
    GEBURTSDATUM
    -0.76
     AssemblyCulture
    -0.76
    WebVitals
    -0.75
    tonsoft
    -0.74
     kaarangay
    -0.73
    клопе
    -0.70
    POSITIVE LOGITS
     aka
    0.56
    ader
    0.53
    _,
    0.51
    lims
    0.51
     dont
    0.49
     Pugh
    0.48
     Die
    0.47
    copyWith
    0.47
     Zimmerman
    0.47
     Productions
    0.47
    Activations Density 1.472%

    No Known Activations