© 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. 5-GEMMASCOPE-RES-16K
    11. 15939
    Prev
    Next
    INDEX
    Explanations

    phrases and structures that express conditions, comparisons, and contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.76
    jména
    -0.60
    ykite
    -0.60
     Romains
    -0.59
     eſt
    -0.59
    ArrowToggle
    -0.57
     juſ
    -0.55
     poveznice
    -0.54
     Manns
    -0.53
     universale
    -0.53
    POSITIVE LOGITS
     že
    0.94
     что
    0.90
     що
    0.87
     że
    0.86
     który
    0.86
     ktorý
    0.82
     które
    0.82
     jakie
    0.81
     שח
    0.81
     who
    0.80
    Activations Density 0.073%

    No Known Activations