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. 16-GEMMASCOPE-RES-16K
    6. 6760
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to limits and convergence

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

    Mathematical limits or approaching infinity

    np_acts-logits-general · gemini-2.0-flash

    approaching limits

    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
     loisirs
    -0.67
    intenant
    -0.59
     réjou
    -0.56
    yní
    -0.56
     lachen
    -0.55
     circonst
    -0.52
     décontract
    -0.51
     embaraz
    -0.51
     sociala
    -0.50
     buoni
    -0.50
    POSITIVE LOGITS
    slowly
    0.75
     slowly
    0.69
    anglès
    0.65
    GOTREF
    0.64
     gradually
    0.62
     ChromeDriver
    0.62
     gradual
    0.59
    趨
    0.59
    SharedDtor
    0.58
    AndEndTag
    0.57
    Activations Density 1.108%

    No Known Activations