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. 12469
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistics related to populations and counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     pat
    -0.48
    teig
    -0.43
    assertNull
    -0.43
    ActivityCompat
    -0.41
    bar
    -0.41
    melidir
    -0.40
    item
    -0.40
     N
    -0.40
    piram
    -0.39
    delwed
    -0.39
    POSITIVE LOGITS
     Efq
    1.00
    TagMode
    0.93
    thousands
    0.86
     يتيمه
    0.83
     doubtnut
    0.82
     thousands
    0.81
     crdi
    0.76
    CloseOperation
    0.76
    IUrlHelper
    0.76
     cdti
    0.75
    Activations Density 0.181%

    No Known Activations