© 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. 3119
    Prev
    Next
    INDEX
    Explanations

    references to scientific research papers and methodologies

    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
    verständlich
    -0.62
    verständ
    -0.61
    ("")){
    -0.61
    kwds
    -0.60
    roek
    -0.58
    sätzlich
    -0.58
     \%}$
    -0.58
    кономі
    -0.57
    "]),
    -0.56
    TypedDataSet
    -0.56
    POSITIVE LOGITS
    -
    1.42
    expandindo
    0.91
    Lähteet
    0.72
     jurídico
    0.72
    ‑
    0.70
     leaſt
    0.69
    出版年
    0.69
    ‐
    0.69
    Chham
    0.69
     firſt
    0.68
    Activations Density 1.505%

    No Known Activations