© 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. 11-GEMMASCOPE-RES-16K
    11. 13033
    Prev
    Next
    INDEX
    Explanations

    terms related to ratings and grading systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Наводи
    -0.79
    knecht
    -0.73
     kasarigan
    -0.70
    loroethene
    -0.68
    ientôt
    -0.68
    riwal
    -0.68
    MoveNext
    -0.68
     abbond
    -0.67
     endregion
    -0.67
    berdayakan
    -0.66
    POSITIVE LOGITS
     rating
    1.12
     ratings
    1.10
     Ratings
    1.09
     Rating
    1.05
    Rating
    0.87
     grades
    0.85
     grade
    0.84
    rating
    0.81
    gdx
    0.81
     RATING
    0.80
    Activations Density 0.131%

    No Known Activations