© 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. 7-GEMMASCOPE-RES-16K
    11. 9805
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific concepts or terminology related to advanced topics in physics and medicine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Caw
    -1.14
     Madonna
    -1.12
    Madonna
    -1.10
    Портал
    -1.06
     Hawthorne
    -0.97
     Sunderland
    -0.96
     Lohan
    -0.96
    uari
    -0.95
    Geplaatst
    -0.94
     Iggy
    -0.92
    POSITIVE LOGITS
    лә
    0.75
    sunrise
    0.74
     Linde
    0.72
    т
    0.72
     Lin
    0.71
    Сол
    0.71
     Er
    0.70
    Jeux
    0.70
     Il
    0.69
     Arora
    0.69
    Activations Density 2.649%

    No Known Activations