© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 892
    Prev
    Next
    INDEX
    Explanations

    expressions related to long-term trends or averages, particularly in a scientific or statistical context

    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
     médicale
    -0.65
    ıştı
    -0.58
     CreateTagHelper
    -0.57
    фин
    -0.56
     aanges
    -0.55
    orus
    -0.55
    enumi
    -0.54
     élégante
    -0.54
    tierten
    -0.53
     hospitales
    -0.53
    POSITIVE LOGITS
     longterm
    1.16
    fristi
    0.90
    fristig
    0.85
    長期
    0.84
    长期
    0.76
     jangka
    0.75
     BoxFit
    0.74
    term
    0.71
     permanent
    0.67
    xaml
    0.66
    Activations Density 0.229%

    No Known Activations