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. 3710
    Prev
    Next
    INDEX
    Explanations

    instances of medical terminology and clinical trial references

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

    Numbers, especially "one", "two", "three"

    np_acts-logits-general · gemini-2.0-flash

    numbers

    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
    addContainerGap
    -0.59
    ItemBackground
    -0.57
     CreateTagHelper
    -0.57
    GIVEREF
    -0.54
    شهاد
    -0.53
    WindowConstants
    -0.52
    ksikon
    -0.51
    SPECIFIC
    -0.49
     саме
    -0.49
    kmale
    -0.49
    POSITIVE LOGITS
     two
    1.26
     three
    1.04
     one
    0.95
    two
    0.94
     deux
    0.94
     four
    0.93
     zwei
    0.89
     trois
    0.85
     five
    0.85
     TWO
    0.84
    Activations Density 0.396%

    No Known Activations