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. 5-GEMMASCOPE-RES-16K
    6. 1273
    Prev
    Next
    INDEX
    Explanations

    formatted strings and placeholders commonly used in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nonUne
    -0.78
     ModelExpression
    -0.72
    
    -0.71
    ()));
    
    -0.70
    دانشنامهٔ
    -0.68
     Wiktionnaire
    -0.68
    '));
    
    -0.65
     [],
    
    -0.64
     sqlSession
    -0.64
    orsche
    -0.64
    POSITIVE LOGITS
    BeginContext
    0.66
    withIdentifier
    0.61
    modb
    0.57
    DialogInterface
    0.55
    abspath
    0.54
    NgModule
    0.53
    Література
    0.49
     ویکی‌پدی
    0.48
    ulsory
    0.48
    LayoutConstraint
    0.47
    Activations Density 0.027%

    No Known Activations