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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 2562
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical charge and currents

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

    Appearance of "charge" followed by a related word

    np_acts-logits-general · gemini-2.0-flash

    electrical charge and current

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    醐
    -0.78
     SDLK
    -0.75
    lgari
    -0.75
     muualla
    -0.75
     שוליים
    -0.74
     تانيه
    -0.71
     Quij
    -0.68
     للمعارف
    -0.68
     blest
    -0.68
     bint
    -0.68
    POSITIVE LOGITS
     charges
    0.79
     Charges
    0.70
    charges
    0.69
    CHARGE
    0.69
    Charges
    0.66
    charge
    0.63
     charge
    0.61
     Charge
    0.58
    Charge
    0.57
     plates
    0.56
    Activations Density 0.059%

    No Known Activations