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. 12-GEMMASCOPE-RES-16K
    6. 12474
    Prev
    Next
    INDEX
    Explanations

    scientific terms and measurements related to particle physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    slf
    -0.48
     you
    -0.45
     Rans
    -0.45
     visitors
    -0.44
     sehari
    -0.44
    ↵↵
    -0.43
     interviews
    -0.43
    Flo
    -0.43
     person
    -0.42
     staff
    -0.42
    POSITIVE LOGITS
     propOrder
    0.86
     kasarigan
    0.80
     indisponible
    0.78
     ainfi
    0.77
     auffi
    0.77
    SharedCtor
    0.76
     extrapolated
    0.75
     JSONException
    0.75
     InputDecoration
    0.74
    InputBorder
    0.74
    Activations Density 1.898%

    No Known Activations