© 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. 8-GEMMASCOPE-RES-16K
    11. 13784
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to improvement and enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PathVariable
    -0.68
     HasFactory
    -0.64
     Koz
    -0.61
    ers
    -0.58
    yl
    -0.57
     Kos
    -0.55
    zk
    -0.55
     k
    -0.53
    ek
    -0.51
     listrik
    -0.51
    POSITIVE LOGITS
     Improvements
    1.54
     improvement
    1.52
    improve
    1.48
     improvements
    1.47
     Improvement
    1.47
    Improvements
    1.47
    esserung
    1.42
     improves
    1.42
    Improve
    1.42
    Improvement
    1.41
    Activations Density 0.109%

    No Known Activations