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. 21-GEMMASCOPE-RES-16K
    6. 14871
    Prev
    Next
    INDEX
    Explanations

    references to Java programming language constructs and class methods related to server configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uesia
    -0.49
    Personal
    -0.46
    tinyos
    -0.45
    ItemBackground
    -0.43
    ptonshire
    -0.41
    BarButtonItem
    -0.41
     personal
    -0.41
    쉬
    -0.40
    specialchars
    -0.40
    敬
    -0.40
    POSITIVE LOGITS
     للمعارف
    0.72
    Autoritní
    0.70
    tagHelperRunner
    0.68
     nonatomic
    0.66
     Савезне
    0.64
    almaz
    0.62
     nahilalakip
    0.61
     المعيارى
    0.60
     дописавши
    0.60
     cherchés
    0.58
    Activations Density 0.171%

    No Known Activations