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. 0-GEMMASCOPE-RES-16K
    6. 6894
    Prev
    Next
    INDEX
    Explanations

    references to specific viral strains or proteins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.84
    yakarta
    -0.83
    Santis
    -0.78
    ագրություններ
    -0.77
    ChildScrollView
    -0.76
    persky
    -0.72
     propOrder
    -0.69
    #+#
    -0.67
     autorytatywna
    -0.67
     سكانية
    -0.66
    POSITIVE LOGITS
    VR
    1.54
    vr
    1.50
     VR
    1.45
     vr
    1.15
    mr
    0.91
     Vr
    0.89
    Vr
    0.88
    nr
    0.78
    pr
    0.78
    NR
    0.78
    Activations Density 0.084%

    No Known Activations