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. 5254
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to diffusion and critical scaling

    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
    برا
    -0.51
    Bayes
    -0.51
     sister
    -0.47
    ougou
    -0.46
    xus
    -0.46
     Pal
    -0.45
     Chi
    -0.45
     tal
    -0.45
    asker
    -0.44
     senior
    -0.43
    POSITIVE LOGITS
    AndEndTag
    0.85
    ValueStyle
    0.83
     مشين
    0.79
     jsPsych
    0.77
    setVerticalGroup
    0.77
    Дереккөздер
    0.74
     ExecuteAsync
    0.74
    ఔ
    0.73
    AnchorStyles
    0.72
     initComponents
    0.71
    Activations Density 1.933%

    No Known Activations