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. 5-GEMMASCOPE-RES-16K
    6. 2570
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to technical procedures and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.49
    EndProject
    -0.47
    DockStyle
    -0.47
    windowFixed
    -0.45
    nos
    -0.44
    ig
    -0.43
    WebVitals
    -0.42
     चीज़ों
    -0.41
    BorderLayout
    -0.41
    </h2>
    -0.39
    POSITIVE LOGITS
     FetchType
    0.79
    DoubleQuotes
    0.77
    principalTable
    0.76
     OMITBAD
    0.75
    הערות
    0.74
     kasarigan
    0.71
    IsContent
    0.71
    商品説明
    0.67
     متعلقه
    0.66
     للمعارف
    0.66
    Activations Density 0.527%

    No Known Activations