Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6190
    Prev
    Next
    INDEX
    Explanations

    mathematical structures, particularly matrices and arrays

    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
    ις
    -0.69
     هو
    -0.67
     stuff
    -0.65
     Rois
    -0.59
    показания
    -0.58
     حول
    -0.57
     around
    -0.56
     turi
    -0.55
    =@"
    -0.55
    psack
    -0.55
    POSITIVE LOGITS
     étoit
    0.81
    SequentialGroup
    0.81
     Abonnez
    0.81
    EndInit
    0.80
     Inscrivez
    0.78
    BeginContext
    0.76
     Partagez
    0.75
    AddTagHelper
    0.74
    الدراسه
    0.73
    ":[{
    0.72
    Activations Density 0.096%

    No Known Activations