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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13-GEMMASCOPE-RES-16K
    6. 7289
    Prev
    Next
    INDEX
    Explanations

    blocks of code or programming elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (
    -0.61
    bleiben
    -0.55
    чан
    -0.52
    an
    -0.51
    nya
    -0.50
     Dolan
    -0.49
    angal
    -0.49
     bì
    -0.48
     (
    -0.48
     сезоне
    -0.47
    POSITIVE LOGITS
    DoubleQuotes
    1.00
    存于互联网档案馆
    1.00
     فريبيس
    0.95
    \{\\
    0.89
    AddTagHelper
    0.82
    expandindo
    0.81
    NOPQRST
    0.79
     InputDecoration
    0.79
     Normdatei
    0.78
    tymologie
    0.77
    Activations Density 0.385%

    No Known Activations