© 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. 3-GEMMASCOPE-RES-16K
    11. 13126
    Prev
    Next
    INDEX
    Explanations

    phrases related to enabling or disabling software features and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bolista
    -0.58
     прожи
    -0.54
    |}{
    -0.54
     الحره
    -0.54
     réactions
    -0.54
     terecht
    -0.53
     químicas
    -0.53
    '],$
    -0.51
     químico
    -0.51
    érité
    -0.51
    POSITIVE LOGITS
    ScopeManager
    0.73
     uninstall
    0.68
     disable
    0.68
     deactivate
    0.67
    Disable
    0.65
     suspend
    0.64
     reinstall
    0.63
     uninstalled
    0.63
     suspending
    0.62
    DISABLE
    0.61
    Activations Density 0.322%

    No Known Activations