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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 16-GEMMASCOPE-RES-16K
    6. 1535
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols typically used in scientific papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text within brackets (often figures/references)

    np_acts-logits-general · gemini-2.0-flash

    reduction two hourskb DNA fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NDEBUG
    -0.66
     onCancelled
    -0.64
     florales
    -0.61
    enumi
    -0.57
     digitais
    -0.56
    AsUp
    -0.54
     Saltar
    -0.54
     Перейти
    -0.53
     Italijani
    -0.52
     Expédié
    -0.52
    POSITIVE LOGITS
    InjectAttribute
    0.83
    LookAnd
    0.81
    AutoScale
    0.77
    parsedMessage
    0.77
    WebControls
    0.70
     typelib
    0.68
    __':
    0.67
    rawDesc
    0.66
    homonymie
    0.66
    StoryboardSegue
    0.65
    Activations Density 8.792%

    No Known Activations