© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2508
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific publications and formal metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.71
    存于互联网档案馆
    -0.60
    chengladbach
    -0.58
    aternion
    -0.56
     GBIF
    -0.55
     للمعارف
    -0.54
    原始内容存档于
    -0.54
     Normdatei
    -0.53
    тору
    -0.52
    WebVitals
    -0.52
    POSITIVE LOGITS
     contrasting
    0.71
     exaggerate
    0.60
     sarcasm
    0.60
     Contrast
    0.56
     contrasts
    0.56
     provoc
    0.56
    Contrast
    0.56
     paradoxical
    0.54
     contrast
    0.54
    __":
    0.54
    Activations Density 2.855%

    No Known Activations