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. 10883
    Prev
    Next
    INDEX
    Explanations

    verbs and actions related to the usage of technology and magical abilities

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

    preceding "to", "in", "with", "that"

    np_acts-logits-general · gemini-2.0-flash

    regarding previous statements

    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
     Надо
    -1.08
     daß
    -1.03
    Надо
    -1.01
    けっこう
    -0.94
     freilich
    -0.92
     läßt
    -0.88
     надо
    -0.88
     jedenfalls
    -0.87
     guère
    -0.86
     ;-)
    -0.85
    POSITIVE LOGITS
     hierbei
    0.97
     anteriormente
    0.88
     entirety
    0.86
     demnach
    0.83
    ⅗
    0.82
    Furthermore
    0.81
     Furthermore
    0.80
     welcher
    0.79
     possu
    0.79
     Lastly
    0.77
    Activations Density 1.505%

    No Known Activations