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. 10816
    Prev
    Next
    INDEX
    Explanations

    the verb "do" in various forms and contexts

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

    "do" followed by "not" suggesting negation

    np_acts-logits-general · gemini-2.0-flash

    do not, do so, do this

    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
     indisponible
    -0.67
    SuccessListener
    -0.61
    "}")
    -0.61
    mientos
    -0.59
    います
    -0.57
    Portale
    -0.57
     متعلقه
    -0.54
     <<<<<<<<<<<<<<
    -0.53
    ựu
    -0.52
     Pingback
    -0.51
    POSITIVE LOGITS
    omsday
    0.83
     things
    0.72
     nothing
    0.70
     وتسجيلات
    0.66
     homework
    0.66
     wonders
    0.66
    ppler
    0.66
     THINGS
    0.64
    ofus
    0.64
    azón
    0.64
    Activations Density 0.245%

    No Known Activations