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. 15-GEMMASCOPE-RES-16K
    6. 2773
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS code structure and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getHeight
    -0.74
     elevation
    -0.68
    queryInterface
    -0.66
    setVerticalGroup
    -0.64
    writeFieldEnd
    -0.61
     elevations
    -0.58
    Höhe
    -0.57
     height
    -0.55
    頂
    -0.55
    UnsafeEnabled
    -0.55
    POSITIVE LOGITS
    extAlignment
    0.52
    fullWidth
    0.50
     Corintios
    0.46
    ^{(\
    0.46
     estí
    0.44
    ampingi
    0.43
     boyfriend
    0.43
    ئت
    0.42
    litz
    0.42
    marginHorizontal
    0.42
    Activations Density 0.141%

    No Known Activations