© 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. 16-GEMMASCOPE-RES-16K
    11. 1822
    Prev
    Next
    INDEX
    Explanations

    elements related to coding and programming tasks involving the Gulp build system, particularly focusing on minification and file management

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

    Code using gulp and file operations

    np_acts-logits-general · gemini-2.0-flash

    gulp build tool and chaining methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tissue
    -0.51
     tissue
    -0.50
    Tissue
    -0.47
    fjspx
    -0.47
    retas
    -0.45
     sobremesa
    -0.44
    скай
    -0.44
     bevestig
    -0.43
     medida
    -0.43
     table
    -0.43
    POSITIVE LOGITS
    DockStyle
    1.06
     Roskov
    0.80
     Majefty
    0.78
     виправивши
    0.77
     ExecuteAsync
    0.77
     Anſ
    0.76
     /\.
    0.72
    parsedMessage
    0.72
    ContentAsync
    0.71
     Monfieur
    0.69
    Activations Density 0.060%

    No Known Activations