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. 2339
    Prev
    Next
    INDEX
    Explanations

    scientific terms and chemical components related to molecular biology and biochemistry

    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
    errHandler
    -0.82
    ArrowToggle
    -0.80
     Италијани
    -0.76
     kasarigan
    -0.76
    contentLoaded
    -0.74
    __':
    -0.74
    Rüyada
    -0.72
     CWE
    -0.72
     '\\;'
    -0.71
    invokeLater
    -0.71
    POSITIVE LOGITS
    NOPQRST
    0.83
    neſs
    0.62
    ſel
    0.59
     rowspan
    0.54
    РАЗ
    0.53
     Dalai
    0.52
    󠁢
    0.52
    #+#
    0.51
    ãng
    0.51
    AnchorStyles
    0.50
    Activations Density 0.273%

    No Known Activations