Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11026
    Prev
    Next
    INDEX
    Explanations

    components related to electrical systems and devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    electrical circuits and switches

    np_acts-logits-general · gemini-2.0-flash

    electrical switches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.87
    ⓧ
    -0.79
     Roskov
    -0.65
    存于互联网档案馆
    -0.63
     Frei
    -0.62
    ISupport
    -0.61
     cheering
    -0.61
     resourceCulture
    -0.60
     Hille
    -0.57
    navBar
    -0.57
    POSITIVE LOGITS
     circuit
    1.01
     fuse
    1.01
     breaker
    0.97
     breakers
    0.93
     Circuit
    0.86
     Breakers
    0.85
    Circuit
    0.84
     plug
    0.84
     switch
    0.84
     fuses
    0.83
    Activations Density 0.132%

    No Known Activations