© 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. 19-GEMMASCOPE-RES-16K
    11. 15917
    Prev
    Next
    INDEX
    Explanations

    phrases related to shortcuts and efficiency, particularly in processes or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTS
    -0.49
     légale
    -0.47
     يتيمه
    -0.47
    reten
    -0.43
    umbus
    -0.42
    ArrowToggle
    -0.41
    DockStyle
    -0.40
    োগ
    -0.40
     rinnov
    -0.39
    ätzliche
    -0.39
    POSITIVE LOGITS
     shortcuts
    2.02
     shortcut
    1.99
     convenience
    1.63
     Shortcuts
    1.56
     Shortcut
    1.51
     simplify
    1.51
    shortcuts
    1.50
    shortcut
    1.46
     Convenience
    1.45
     lazy
    1.41
    Activations Density 0.431%

    No Known Activations