© 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. 10-GEMMASCOPE-RES-16K
    11. 15533
    Prev
    Next
    INDEX
    Explanations

    instances of the word "switch" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     denaro
    -0.85
    ymce
    -0.81
    thâu
    -0.81
     humaines
    -0.80
     שוליים
    -0.79
     figliu
    -0.77
     труда
    -0.77
    Documented
    -0.76
     Corel
    -0.75
     giusti
    -0.74
    POSITIVE LOGITS
     Switch
    1.77
     switches
    1.70
     switch
    1.69
     SWITCH
    1.66
    Switch
    1.64
     Switches
    1.57
    SWITCH
    1.55
     switched
    1.50
    switches
    1.46
     switching
    1.43
    Activations Density 0.065%

    No Known Activations