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. 11784
    Prev
    Next
    INDEX
    Explanations

    references to indoor and outdoor environments

    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
    BeginContext
    -0.86
    المناصب
    -0.85
    MigrationBuilder
    -0.83
    SuccessListener
    -0.82
    UnknownFieldSet
    -0.82
    LabelTagHelper
    -0.80
     Geraadpleegd
    -0.80
    ']?>
    -0.80
    JspWriter
    -0.78
     وتسجيلات
    -0.78
    POSITIVE LOGITS
     outdoor
    1.72
     indoor
    1.71
     Indoor
    1.69
    Outdoor
    1.64
     Outdoor
    1.62
    outdoor
    1.58
    Indoor
    1.50
     outdoors
    1.43
     indoors
    1.36
    indoor
    1.33
    Activations Density 0.068%

    No Known Activations