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. 16-GEMMASCOPE-RES-16K
    6. 4585
    Prev
    Next
    INDEX
    Explanations

    references to coding or programming concepts related to VBA

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

    VBA and Excel code snippets

    np_acts-logits-general · gemini-2.0-flash

    if/then conditional logic

    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
     pinulongan
    -0.73
    RegressionTest
    -0.67
     autorytatywna
    -0.60
    脚注の使い方
    -0.58
    ::::::::
    -0.58
    },{
    
    -0.56
    原始内容存档于
    -0.55
    atilde
    -0.55
    ęk
    -0.55
    :+:
    -0.54
    POSITIVE LOGITS
     VBA
    0.56
     Moray
    0.46
     Fórmula
    0.45
     naught
    0.45
     nervosa
    0.45
     typelib
    0.44
    ionage
    0.43
     Ooster
    0.43
     blanks
    0.43
    西兰
    0.42
    Activations Density 1.164%

    No Known Activations