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. 16-GEMMASCOPE-RES-16K
    6. 12266
    Prev
    Next
    INDEX
    Explanations

    expressions of high praise regarding people or experiences

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

    Superlatives with "ever"

    np_acts-logits-general · gemini-2.0-flash

    best experiences ever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.63
    bootstrapcdn
    -0.58
     jspb
    -0.55
     nere
    -0.53
     doel
    -0.51
    awtextra
    -0.49
    ">:
    -0.48
    {#
    -0.48
     متعلقه
    -0.48
     Anfitrión
    -0.47
    POSITIVE LOGITS
     ever
    0.90
     EVER
    0.81
     jemals
    0.72
     imaginable
    0.68
    atever
    0.65
    ContentAsync
    0.64
     anywhere
    0.60
     anybody
    0.60
     anyone
    0.59
     whatsoever
    0.59
    Activations Density 0.091%

    No Known Activations