© 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. 3534
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specific quantities or measurements, often involving numeric values or comparative phrases

    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
    лару
    -0.52
     ctypes
    -0.50
    vieja
    -0.49
    viewType
    -0.48
     Palms
    -0.48
    EMIA
    -0.46
    جاد
    -0.45
     inso
    -0.45
     eventualmente
    -0.45
     Patterns
    -0.44
    POSITIVE LOGITS
     slightest
    0.86
    tagHelperRunner
    0.84
     EVERY
    0.81
     every
    0.80
     absolutamente
    0.80
    EVERY
    0.79
     виправивши
    0.78
     ModelExpression
    0.75
     EVERYTHING
    0.73
     iota
    0.73
    Activations Density 0.124%

    No Known Activations