© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5423
    Prev
    Next
    INDEX
    Explanations

    references to directional lighting and related parameters in programming contexts

    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
    +#+#
    -1.04
    e
    -0.91
    //
    -0.89
     estimés
    -0.87
    endphp
    -0.85
    ंदीखरीदारी
    -0.85
    a
    -0.84
    NewUrlParser
    -0.83
    dotenv
    -0.82
     endregion
    -0.81
    POSITIVE LOGITS
    ,$_
    0.77
    BibitemShut
    0.72
     Theſe
    0.66
     doubtnut
    0.64
    Cordialement
    0.62
    bibinfo
    0.62
    Lycka
    0.62
    ⎯
    0.60
     themſelves
    0.60
    ῶ
    0.59
    Activations Density 0.697%

    No Known Activations