© 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. 3-GEMMASCOPE-RES-16K
    11. 8066
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and their citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -1.02
     للاسماء
    -0.95
     виправивши
    -0.80
     HasFactory
    -0.79
     <<<<<<<<<<<<<<
    -0.78
     Signalez
    -0.74
     تضيفلها
    -0.74
     viewDidLoad
    -0.73
    DoubleQuotes
    -0.70
    Espèce
    -0.68
    POSITIVE LOGITS
     int
    0.55
    بوابة
    0.50
     måtte
    0.49
    ỗi
    0.46
    each
    0.45
     dalamnya
    0.43
    henti
    0.42
    SerializeField
    0.41
    every
    0.41
    هر
    0.40
    Activations Density 0.421%

    No Known Activations