Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12328
    Prev
    Next
    INDEX
    Explanations

    programming and command-related terminology, particularly in the context of software and scripts

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

    Commands and code snippets

    np_acts-logits-general · gemini-2.0-flash

    command line arguments

    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
    .")
    
    -0.56
    '>{
    -0.55
    )");
    
    -0.53
    >");
    
    -0.52
    smarty
    -0.52
    SafeMath
    -0.51
    %")
    -0.51
    beforeEach
    -0.50
    !")
    
    -0.50
    archiviato
    -0.49
    POSITIVE LOGITS
     "..\..\..\
    0.70
     malheureux
    0.63
     prisonniers
    0.61
     réfugiés
    0.61
     Roskov
    0.59
     mijne
    0.59
    ]--;
    0.58
     Whitening
    0.57
     curvas
    0.57
    RegistryLite
    0.57
    Activations Density 1.244%

    No Known Activations