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. 18-GEMMASCOPE-RES-16K
    6. 1129
    Prev
    Next
    INDEX
    Explanations

    references to the concept of nature

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

    the word "nature"

    np_acts-logits-general · gemini-2.0-flash

    Nature has or of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -1.13
     تضيفلها
    -0.81
     Efq
    -0.75
     ***!
    -0.74
     SqlCommand
    -0.70
    ChildScrollView
    -0.69
    ModelBuilder
    -0.66
    dymyr
    -0.64
     fhew
    -0.64
     pleaſure
    -0.64
    POSITIVE LOGITS
     Nature
    0.97
     NATURE
    0.97
     nature
    0.89
    Nature
    0.84
    NATURE
    0.74
    nature
    0.72
     natures
    0.69
     natureza
    0.66
     morte
    0.59
     natura
    0.58
    Activations Density 0.064%

    No Known Activations